Refers to any valid JSON-RPC object that can be decoded off the wire, or encoded to be sent.
A notification which does not expect a response.
A request that expects a response.
A response to a request, containing either the result or error.
A successful (non-error) response to a request.
Optional annotations for the client. The client can use annotations to inform how objects are used or displayed
Describes who the intended audience of this object or data is.
It can include multiple entries to indicate content useful for multiple audiences (e.g., \["user", "assistant"]).
Describes how important this data is for operating the server.
A value of 1 means "most important," and indicates that the data is effectively required, while 0 means "least important," and indicates that the data is entirely optional.
The moment the resource was last modified, as an ISO 8601 formatted string.
Should be an ISO 8601 formatted string (e.g., "2025-01-12T15:00:58Z").
Examples: last activity timestamp in an open file, timestamp when the resource was attached, etc.
An opaque token used to represent a cursor for pagination.
A result that indicates success but carries no data.
An optionally-sized icon that can be displayed in a user interface.
A standard URI pointing to an icon resource. May be an HTTP/HTTPS URL or a data: URI with Base64-encoded image data.
Consumers SHOULD take steps to ensure URLs serving icons are from the same domain as the client/server or a trusted domain.
Consumers SHOULD take appropriate precautions when consuming SVGs as they can contain executable JavaScript.
Optional MIME type override if the source MIME type is missing or generic.
For example: "image/png", "image/jpeg", or "image/svg+xml".
Optional array of strings that specify sizes at which the icon can be used.
Each string should be in WxH format (e.g., "48x48", "96x96") or "any" for scalable formats like SVG.
If not provided, the client should assume that the icon can be used at any size.
Optional specifier for the theme this icon is designed for. "light" indicates
the icon is designed to be used with a light background, and "dark" indicates
the icon is designed to be used with a dark background.
If not provided, the client should assume the icon can be used with any theme.
Common params for any request.
The severity of a log message.
These map to syslog message severities, as specified in RFC-5424: [https://datatracker.ietf.org/doc/html/rfc5424#section-6.2.1](https://datatracker.ietf.org/doc/html/rfc5424#section-6.2.1)
Deprecated as of protocol version 2026-07-28 (SEP-2577). Remains in the specification for at least twelve months; see the deprecated features registry.
Represents the contents of a \_meta field, which clients and servers use to attach additional metadata to their interactions.
Certain key names are reserved by MCP for protocol-level metadata; implementations MUST NOT make assumptions about values at these keys. Additionally, specific schema definitions may reserve particular names for purpose-specific metadata, as declared in those definitions.
Valid keys have two segments:
Prefix:
.), followed by a slash (/).-).com.example/ rather than example.com/).modelcontextprotocol or mcp is reserved for MCP use. For example: io.modelcontextprotocol/, dev.mcp/, org.modelcontextprotocol.api/, and com.mcp.tools/ are all reserved. However, com.example.mcp/ is NOT reserved, as the second label is example.Name:
\[a-z0-9A-Z]).-), underscores (\_), or dots (.).General fields: \_meta for more details.
Common params for any notification.
Common params for paginated requests.
An opaque token representing the current pagination position. If provided, the server should return results starting after this cursor.
A progress token, used to associate progress notifications with the original request.
A uniquely identifying ID for a request in JSON-RPC.
Extends MetaObject with additional request-specific fields. All key naming rules from MetaObject apply.
\_meta for more details.If specified, the caller is requesting out-of-band progress notifications for this request (as represented by notifications/progress). The value of this parameter is an opaque token that will be attached to any subsequent notifications. The receiver is not obligated to provide these notifications.
The MCP Protocol Version being used for this request. Required.
For the HTTP transport, this value MUST match the MCP-Protocol-Version
header; otherwise the server MUST return a 400 Bad Request. If the
server does not support the requested version, it MUST return an UnsupportedProtocolVersionError.
Identifies the client software making the request. Required.
The Implementation schema requires name and version; other
fields are optional.
The client's capabilities for this specific request. Required.
Capabilities are declared per-request rather than once at initialization; an empty object means the client supports no optional capabilities. Servers MUST NOT infer capabilities from prior requests.
The desired log level for this request. Optional.
If absent, the server MUST NOT send any notifications/message
notifications for this request. The client opts in to log messages by
explicitly setting a level. Replaces the former logging/setLevel RPC.
Deprecated as of protocol version 2026-07-28 (SEP-2577). Remains in the specification for at least twelve months; see the deprecated features registry.
Common params for any request.
Common result fields.
Indicates the type of the result, which allows the client to determine how to parse the result object.
Servers implementing this protocol version MUST include this field.
For backward compatibility, when a client receives a result from a
server implementing an earlier protocol version (which does not include resultType), the client MUST treat the absent field as "complete".
Indicates the type of a Result object, allowing the client to determine how to parse the response.
complete - the request completed successfully and the result contains the final content. input\_required - the request requires additional input and the result contains an InputRequiredResult object with instructions for the client to provide additional input before retrying the original request.
The sender or recipient of messages and data in a conversation.
The error type that occurred.
A short description of the error. The message SHOULD be limited to a concise single sentence.
Additional information about the error. The value of this member is defined by the sender (e.g. detailed error information, nested errors etc.).
A JSON-RPC error indicating that an internal error occurred on the receiver. This error is returned when the receiver encounters an unexpected condition that prevents it from fulfilling the request.
A short description of the error. The message SHOULD be limited to a concise single sentence.
Additional information about the error. The value of this member is defined by the sender (e.g. detailed error information, nested errors etc.).
The error type that occurred.
A JSON-RPC error indicating that the method parameters are invalid or malformed.
In MCP, this error is returned in various contexts when request parameters fail validation:
A short description of the error. The message SHOULD be limited to a concise single sentence.
Additional information about the error. The value of this member is defined by the sender (e.g. detailed error information, nested errors etc.).
The error type that occurred.
A JSON-RPC error indicating that the request is not a valid request object. This error is returned when the message structure does not conform to the JSON-RPC 2.0 specification requirements for a request (e.g., missing required fields like jsonrpc or method, or using invalid types for these fields).
A short description of the error. The message SHOULD be limited to a concise single sentence.
Additional information about the error. The value of this member is defined by the sender (e.g. detailed error information, nested errors etc.).
The error type that occurred.
A JSON-RPC error indicating that the requested method does not exist or is not available.
In MCP, a server returns this error when a client invokes a method the server does not implement — either a genuinely unknown method, or one gated behind a server capability the server did not advertise (e.g., calling prompts/list when the prompts capability was not advertised).
A request that requires a client capability the client did not declare is signalled instead by MissingRequiredClientCapabilityError (-32003).
A short description of the error. The message SHOULD be limited to a concise single sentence.
Additional information about the error. The value of this member is defined by the sender (e.g. detailed error information, nested errors etc.).
The error type that occurred.
Error code returned when a server requires a client capability that was
not declared in the request's clientCapabilities.
Returned when processing a request requires a capability the client did not
declare in clientCapabilities. For HTTP, the response status code MUST be 400 Bad Request.
A JSON-RPC error indicating that invalid JSON was received by the server. This error is returned when the server cannot parse the JSON text of a message.
A short description of the error. The message SHOULD be limited to a concise single sentence.
Additional information about the error. The value of this member is defined by the sender (e.g. detailed error information, nested errors etc.).
The error type that occurred.
Error code returned when the request's protocol version is not supported by the server.
Returned when the request's protocol version is unknown to the server or
unsupported (e.g., a known experimental or draft version the server has
chosen not to implement). For HTTP, the response status code MUST be 400 Bad Request.
Audio provided to or from an LLM.
The base64-encoded audio data.
The MIME type of the audio. Different providers may support different audio types.
Optional annotations for the client.
The URI of this resource.
The MIME type of this resource, if known.
A base64-encoded string representing the binary data of the item.
The contents of a resource, embedded into a prompt or tool call result.
It is up to the client how best to render embedded resources for the benefit of the LLM and/or the user.
\{
"type": "resource",
"resource": \{
"uri": "file:///project/src/main.rs",
"mimeType": "text/x-rust",
"text": "fn main() \{\n println!(\\"Hello world!\\");\n}"
},
"annotations": \{
"audience": \["user", "assistant"],
"priority": 0.7,
"lastModified": "2025-05-03T14:30:00Z"
}
} Optional annotations for the client.
An image provided to or from an LLM.
The base64-encoded image data.
The MIME type of the image. Different providers may support different image types.
Optional annotations for the client.
A resource that the server is capable of reading, included in a prompt or tool call result.
Note: resource links returned by tools are not guaranteed to appear in the results of resources/list requests.
Optional set of sized icons that the client can display in a user interface.
Clients that support rendering icons MUST support at least the following MIME types:
image/png - PNG images (safe, universal compatibility)image/jpeg (and image/jpg) - JPEG images (safe, universal compatibility)Clients that support rendering icons SHOULD also support:
image/svg+xml - SVG images (scalable but requires security precautions)image/webp - WebP images (modern, efficient format)Intended for programmatic or logical use, but used as a display name in past specs or fallback (if title isn't present).
Intended for UI and end-user contexts — optimized to be human-readable and easily understood, even by those unfamiliar with domain-specific terminology.
If not provided, the name should be used for display (except for Tool,
where annotations.title should be given precedence over using name,
if present).
The URI of this resource.
A description of what this resource represents.
This can be used by clients to improve the LLM's understanding of available resources. It can be thought of like a "hint" to the model.
The MIME type of this resource, if known.
Optional annotations for the client.
The size of the raw resource content, in bytes (i.e., before base64 encoding or any tokenization), if known.
This can be used by Hosts to display file sizes and estimate context window usage.
Text provided to or from an LLM.
The text content of the message.
Optional annotations for the client.
The URI of this resource.
The MIME type of this resource, if known.
The text of the item. This must only be set if the item can actually be represented as text (not binary data).
A request from the client to the server, to ask for completion options.
\{
"jsonrpc": "2.0",
"id": "completion-example",
"method": "completion/complete",
"params": \{
"\_meta": \{
"io.modelcontextprotocol/protocolVersion": "2026-07-28",
"io.modelcontextprotocol/clientInfo": \{
"name": "ExampleClient",
"version": "1.0.0"
},
"io.modelcontextprotocol/clientCapabilities": \{}
},
"ref": \{
"type": "ref/prompt",
"name": "code\_review"
},
"argument": \{
"name": "language",
"value": "py"
}
}
} Parameters for a completion/complete request.
\{
"\_meta": \{
"io.modelcontextprotocol/protocolVersion": "2026-07-28",
"io.modelcontextprotocol/clientInfo": \{
"name": "ExampleClient",
"version": "1.0.0"
},
"io.modelcontextprotocol/clientCapabilities": \{}
},
"ref": \{
"type": "ref/prompt",
"name": "code\_review"
},
"argument": \{
"name": "language",
"value": "py"
}
} \{
"\_meta": \{
"io.modelcontextprotocol/protocolVersion": "2026-07-28",
"io.modelcontextprotocol/clientInfo": \{
"name": "ExampleClient",
"version": "1.0.0"
},
"io.modelcontextprotocol/clientCapabilities": \{}
},
"ref": \{
"type": "ref/prompt",
"name": "code\_review"
},
"argument": \{
"name": "framework",
"value": "fla"
},
"context": \{
"arguments": \{
"language": "python"
}
}
} The argument's information
The name of the argument
The value of the argument to use for completion matching.
Additional, optional context for completions
Optionalarguments?: \{ \[key: string]: string }Previously-resolved variables in a URI template or prompt.
A successful response from the server for a completion/complete request.
The result returned by the server for a completion/complete request.
Indicates the type of the result, which allows the client to determine how to parse the result object.
Servers implementing this protocol version MUST include this field.
For backward compatibility, when a client receives a result from a
server implementing an earlier protocol version (which does not include resultType), the client MUST treat the absent field as "complete".
An array of completion values. Must not exceed 100 items.
Optionaltotal?: numberThe total number of completion options available. This can exceed the number of values actually sent in the response.
OptionalhasMore?: booleanIndicates whether there are additional completion options beyond those provided in the current response, even if the exact total is unknown.
Identifies a prompt.
Intended for programmatic or logical use, but used as a display name in past specs or fallback (if title isn't present).
Intended for UI and end-user contexts — optimized to be human-readable and easily understood, even by those unfamiliar with domain-specific terminology.
If not provided, the name should be used for display (except for Tool,
where annotations.title should be given precedence over using name,
if present).
A reference to a resource or resource template definition.
The URI or URI template of the resource.
A request from the server to elicit additional information from the user via the client.
\{
"method": "elicitation/create",
"params": \{
"mode": "form",
"message": "Please provide your GitHub username",
"requestedSchema": \{
"type": "object",
"properties": \{
"name": \{
"type": "string",
"title": "GitHub Username",
"description": "Your GitHub username"
}
},
"required": \["name"]
}
}
} The parameters for a request to elicit additional information from the user via the client.
The result returned by the client for an elicitation/create request.
The user action in response to the elicitation.
"accept": User submitted the form/confirmed the action"decline": User explicitly declined the action"cancel": User dismissed without making an explicit choiceThe submitted form data, only present when action is "accept" and mode was "form".
Contains values matching the requested schema.
Omitted for out-of-band mode responses.
The parameters for a request to elicit non-sensitive information from the user via a form in the client.
\{
"mode": "form",
"message": "Please provide your GitHub username",
"requestedSchema": \{
"type": "object",
"properties": \{
"name": \{
"type": "string"
}
},
"required": \["name"]
}
} \{
"mode": "form",
"message": "Please provide your contact information",
"requestedSchema": \{
"type": "object",
"properties": \{
"name": \{
"type": "string",
"description": "Your full name"
},
"email": \{
"type": "string",
"format": "email",
"description": "Your email address"
},
"age": \{
"type": "number",
"minimum": 18,
"description": "Your age"
}
},
"required": \["name", "email"]
}
} The elicitation mode.
The message to present to the user describing what information is being requested.
A restricted subset of JSON Schema. Only top-level properties are allowed, without nesting.
The parameters for a request to elicit information from the user via a URL in the client.
The elicitation mode.
The message to present to the user explaining why the interaction is needed.
The ID of the elicitation, which must be unique within the context of the server. The client MUST treat this ID as an opaque value.
The URL that the user should navigate to.
Use TitledSingleSelectEnumSchema instead. This interface will be removed in a future version.
(Legacy) Display names for enum values. Non-standard according to JSON schema 2020-12.
Restricted schema definitions that only allow primitive types without nested objects or arrays.
Schema for multiple-selection enumeration with display titles for each option.
\{
"type": "array",
"title": "Color Selection",
"description": "Choose your favorite colors",
"minItems": 1,
"maxItems": 2,
"items": \{
"anyOf": \[
\{ "const": "#FF0000", "title": "Red" },
\{ "const": "#00FF00", "title": "Green" },
\{ "const": "#0000FF", "title": "Blue" }
]
},
"default": \["#FF0000", "#00FF00"]
} Optional title for the enum field.
Optional description for the enum field.
Minimum number of items to select.
Maximum number of items to select.
Schema for array items with enum options and display labels.
Array of enum options with values and display labels.
Optional default value.
Schema for single-selection enumeration with display titles for each option.
Optional title for the enum field.
Optional description for the enum field.
Array of enum options with values and display labels.
The enum value.
Display label for this option.
Optional default value.
Schema for multiple-selection enumeration without display titles for options.
Optional title for the enum field.
Optional description for the enum field.
Minimum number of items to select.
Maximum number of items to select.
Schema for the array items.
Array of enum values to choose from.
Optional default value.
Schema for single-selection enumeration without display titles for options.
Optional title for the enum field.
Optional description for the enum field.
Array of enum values to choose from.
Optional default value.
This notification can be sent by either side to indicate that it is cancelling a previously-issued request.
The request SHOULD still be in-flight, but due to communication latency, it is always possible that this notification MAY arrive after the request has already finished.
This notification indicates that the result will be unused, so any associated processing SHOULD cease.
Parameters for a notifications/cancelled notification.
The ID of the request to cancel.
This MUST correspond to the ID of a request previously issued in the same direction.
An optional string describing the reason for the cancellation. This MAY be logged or presented to the user.
JSONRPCNotification of a log message passed from server to client. The client opts in by setting "io.modelcontextprotocol/logLevel" in a request's \_meta.
Deprecated as of protocol version 2026-07-28 (SEP-2577). Remains in the specification for at least twelve months; see the deprecated features registry.
Parameters for a notifications/message notification.
Deprecated as of protocol version 2026-07-28 (SEP-2577). Remains in the specification for at least twelve months; see the deprecated features registry.
The severity of this log message.
An optional name of the logger issuing this message.
The data to be logged, such as a string message or an object. Any JSON serializable type is allowed here.
An out-of-band notification used to inform the receiver of a progress update for a long-running request.
Parameters for a notifications/progress notification.
The progress token which was given in the initial request, used to associate this notification with the request that is proceeding.
The progress thus far. This should increase every time progress is made, even if the total is unknown.
Total number of items to process (or total progress required), if known.
An optional message describing the current progress.
An optional notification from the server to the client, informing it that the list of prompts it offers has changed. This may be issued by servers without any previous subscription from the client.
An optional notification from the server to the client, informing it that the list of resources it can read from has changed. This may be issued by servers without any previous subscription from the client.
A notification from the server to the client, informing it that a resource has changed and may need to be read again. This is only sent for resources the client opted in to via the resourceSubscriptions field of a subscriptions/listen request.
Parameters for a notifications/resources/updated notification.
The URI of the resource that has been updated. This might be a sub-resource of the one that the client actually subscribed to.
Sent by the server as the first message on a subscriptions/listen stream to acknowledge that the subscription has been established and to report which notification types it agreed to honor.
Parameters for a notifications/subscriptions/acknowledged notification.
The subset of requested notification types the server agreed to honor.
Only includes notification types the server actually supports; if the
client requested an unsupported type (e.g., promptsListChanged when
the server has no prompts), it is omitted from this set.
An optional notification from the server to the client, informing it that the list of tools it offers has changed. This may be issued by servers without any previous subscription from the client.
An optional notification from the server to the client, informing it of a completion of a out-of-band elicitation request.
Parameters for a notifications/elicitation/complete notification.
The ID of the elicitation that completed.
A map of server-initiated requests that the client must fulfill. Keys are server-assigned identifiers; values are the request objects.
\{
"github\_login": \{
"method": "elicitation/create",
"params": \{
"mode": "form",
"message": "Please provide your GitHub username",
"requestedSchema": \{
"type": "object",
"properties": \{
"name": \{
"type": "string"
}
},
"required": \["name"]
}
}
},
"capital\_of\_france": \{
"method": "sampling/createMessage",
"params": \{
"messages": \[
\{
"role": "user",
"content": \{
"type": "text",
"text": "What is the capital of France?"
}
}
],
"maxTokens": 100
}
}
} An InputRequiredResult sent by the server to indicate that additional input is needed before the request can be completed.
At least one of inputRequests or requestState MUST be present.
\{
"resultType": "input\_required",
"inputRequests": \{
"github\_login": \{
"method": "elicitation/create",
"params": \{
"message": "Please provide your GitHub username",
"requestedSchema": \{
"type": "object",
"properties": \{
"name": \{
"type": "string"
}
},
"required": \["name"]
}
}
},
"capital\_of\_france": \{
"method": "sampling/createMessage",
"params": \{
"messages": \[
\{
"role": "user",
"content": \{
"type": "text",
"text": "What is the capital of France?"
}
}
],
"maxTokens": 100
}
}
},
"requestState": "eyJsb2NhdGlvbiI6Ik5ldyBZb3JrIn0"
} Indicates the type of the result, which allows the client to determine how to parse the result object.
Servers implementing this protocol version MUST include this field.
For backward compatibility, when a client receives a result from a
server implementing an earlier protocol version (which does not include resultType), the client MUST treat the absent field as "complete".
A map of client responses to server-initiated requests. Keys correspond to the keys in the InputRequests map; values are the client's result for each request.
\{
"github\_login": \{
"action": "accept",
"content": \{
"name": "octocat"
}
},
"capital\_of\_france": \{
"role": "assistant",
"content": \{
"type": "text",
"text": "The capital of France is Paris."
},
"model": "claude-3-sonnet-20240307",
"stopReason": "endTurn"
}
} Used by the client to get a prompt provided by the server.
\{
"jsonrpc": "2.0",
"id": "get-prompt-example",
"method": "prompts/get",
"params": \{
"\_meta": \{
"io.modelcontextprotocol/protocolVersion": "2026-07-28",
"io.modelcontextprotocol/clientInfo": \{
"name": "ExampleClient",
"version": "1.0.0"
},
"io.modelcontextprotocol/clientCapabilities": \{}
},
"name": "code\_review",
"arguments": \{
"code": "def hello():\n print('world')"
}
}
} Parameters for a prompts/get request.
\{
"\_meta": \{
"io.modelcontextprotocol/protocolVersion": "2026-07-28",
"io.modelcontextprotocol/clientInfo": \{
"name": "ExampleClient",
"version": "1.0.0"
},
"io.modelcontextprotocol/clientCapabilities": \{}
},
"name": "code\_review",
"arguments": \{
"code": "def hello():\n print('world')"
}
} The name of the prompt or prompt template.
Arguments to use for templating the prompt.
A successful response from the server for a prompts/get request.
\{
"jsonrpc": "2.0",
"id": "get-prompt-example",
"result": \{
"resultType": "complete",
"description": "Code review prompt",
"messages": \[
\{
"role": "user",
"content": \{
"type": "text",
"text": "Please review this Python code:\ndef hello():\n print('world')"
}
}
]
}
} The result returned by the server for a prompts/get request.
Indicates the type of the result, which allows the client to determine how to parse the result object.
Servers implementing this protocol version MUST include this field.
For backward compatibility, when a client receives a result from a
server implementing an earlier protocol version (which does not include resultType), the client MUST treat the absent field as "complete".
An optional description for the prompt.
Describes a message returned as part of a prompt.
This is similar to SamplingMessage, but also supports the embedding of resources from the MCP server.
Sent from the client to request a list of prompts and prompt templates the server has.
\{
"jsonrpc": "2.0",
"id": "list-prompts-example",
"method": "prompts/list",
"params": \{
"\_meta": \{
"io.modelcontextprotocol/protocolVersion": "2026-07-28",
"io.modelcontextprotocol/clientInfo": \{
"name": "ExampleClient",
"version": "1.0.0"
},
"io.modelcontextprotocol/clientCapabilities": \{}
}
}
} A successful response from the server for a prompts/list request.
\{
"jsonrpc": "2.0",
"id": "list-prompts-example",
"result": \{
"resultType": "complete",
"prompts": \[
\{
"name": "code\_review",
"title": "Request Code Review",
"description": "Asks the LLM to analyze code quality and suggest improvements",
"arguments": \[
\{
"name": "code",
"description": "The code to review",
"required": true
}
],
"icons": \[
\{
"src": "[https://example.com/review-icon.svg](https://example.com/review-icon.svg)",
"mimeType": "image/svg+xml",
"sizes": \["any"]
}
]
}
],
"nextCursor": "next-page-cursor",
"ttlMs": 600000,
"cacheScope": "public"
}
} The result returned by the server for a prompts/list request.
\{
"resultType": "complete",
"prompts": \[
\{
"name": "code\_review",
"title": "Request Code Review",
"description": "Asks the LLM to analyze code quality and suggest improvements",
"arguments": \[
\{
"name": "code",
"description": "The code to review",
"required": true
}
],
"icons": \[
\{
"src": "[https://example.com/review-icon.svg](https://example.com/review-icon.svg)",
"mimeType": "image/svg+xml",
"sizes": \["any"]
}
]
}
],
"nextCursor": "next-page-cursor",
"ttlMs": 600000,
"cacheScope": "public"
} Indicates the type of the result, which allows the client to determine how to parse the result object.
Servers implementing this protocol version MUST include this field.
For backward compatibility, when a client receives a result from a
server implementing an earlier protocol version (which does not include resultType), the client MUST treat the absent field as "complete".
An opaque token representing the pagination position after the last returned result. If present, there may be more results available.
A hint from the server indicating how long (in milliseconds) the client MAY cache this response before re-fetching. Semantics are analogous to HTTP Cache-Control max-age.
Indicates the intended scope of the cached response, analogous to HTTP Cache-Control: public vs Cache-Control: private.
"public": Any client or intermediary (e.g., shared gateway, proxy)
MAY cache the response and serve it to any user."private": Only the requesting user's client MAY cache the response.
Shared caches (e.g., multi-tenant gateways) MUST NOT serve a cached
copy to a different user.A prompt or prompt template that the server offers.
Optional set of sized icons that the client can display in a user interface.
Clients that support rendering icons MUST support at least the following MIME types:
image/png - PNG images (safe, universal compatibility)image/jpeg (and image/jpg) - JPEG images (safe, universal compatibility)Clients that support rendering icons SHOULD also support:
image/svg+xml - SVG images (scalable but requires security precautions)image/webp - WebP images (modern, efficient format)Intended for programmatic or logical use, but used as a display name in past specs or fallback (if title isn't present).
Intended for UI and end-user contexts — optimized to be human-readable and easily understood, even by those unfamiliar with domain-specific terminology.
If not provided, the name should be used for display (except for Tool,
where annotations.title should be given precedence over using name,
if present).
An optional description of what this prompt provides
A list of arguments to use for templating the prompt.
Describes an argument that a prompt can accept.
Intended for programmatic or logical use, but used as a display name in past specs or fallback (if title isn't present).
Intended for UI and end-user contexts — optimized to be human-readable and easily understood, even by those unfamiliar with domain-specific terminology.
If not provided, the name should be used for display (except for Tool,
where annotations.title should be given precedence over using name,
if present).
A human-readable description of the argument.
Whether this argument must be provided.
Sent from the client to request a list of resources the server has.
\{
"jsonrpc": "2.0",
"id": "list-resources-example",
"method": "resources/list",
"params": \{
"\_meta": \{
"io.modelcontextprotocol/protocolVersion": "2026-07-28",
"io.modelcontextprotocol/clientInfo": \{
"name": "ExampleClient",
"version": "1.0.0"
},
"io.modelcontextprotocol/clientCapabilities": \{}
}
}
} A successful response from the server for a resources/list request.
\{
"jsonrpc": "2.0",
"id": "list-resources-example",
"result": \{
"resultType": "complete",
"resources": \[
\{
"uri": "file:///project/src/main.rs",
"name": "main.rs",
"title": "Rust Software Application Main File",
"description": "Primary application entry point",
"mimeType": "text/x-rust",
"icons": \[
\{
"src": "[https://example.com/rust-file-icon.png](https://example.com/rust-file-icon.png)",
"mimeType": "image/png",
"sizes": \["48x48"]
}
]
}
],
"nextCursor": "eyJwYWdlIjogM30=",
"ttlMs": 600000,
"cacheScope": "private"
}
} The result returned by the server for a resources/list request.
\{
"resultType": "complete",
"resources": \[
\{
"uri": "file:///project/src/main.rs",
"name": "main.rs",
"title": "Rust Software Application Main File",
"description": "Primary application entry point",
"mimeType": "text/x-rust",
"icons": \[
\{
"src": "[https://example.com/rust-file-icon.png](https://example.com/rust-file-icon.png)",
"mimeType": "image/png",
"sizes": \["48x48"]
}
]
}
],
"nextCursor": "eyJwYWdlIjogM30=",
"ttlMs": 600000,
"cacheScope": "private"
} Indicates the type of the result, which allows the client to determine how to parse the result object.
Servers implementing this protocol version MUST include this field.
For backward compatibility, when a client receives a result from a
server implementing an earlier protocol version (which does not include resultType), the client MUST treat the absent field as "complete".
An opaque token representing the pagination position after the last returned result. If present, there may be more results available.
A hint from the server indicating how long (in milliseconds) the client MAY cache this response before re-fetching. Semantics are analogous to HTTP Cache-Control max-age.
Indicates the intended scope of the cached response, analogous to HTTP Cache-Control: public vs Cache-Control: private.
"public": Any client or intermediary (e.g., shared gateway, proxy)
MAY cache the response and serve it to any user."private": Only the requesting user's client MAY cache the response.
Shared caches (e.g., multi-tenant gateways) MUST NOT serve a cached
copy to a different user.A known resource that the server is capable of reading.
Optional set of sized icons that the client can display in a user interface.
Clients that support rendering icons MUST support at least the following MIME types:
image/png - PNG images (safe, universal compatibility)image/jpeg (and image/jpg) - JPEG images (safe, universal compatibility)Clients that support rendering icons SHOULD also support:
image/svg+xml - SVG images (scalable but requires security precautions)image/webp - WebP images (modern, efficient format)Intended for programmatic or logical use, but used as a display name in past specs or fallback (if title isn't present).
Intended for UI and end-user contexts — optimized to be human-readable and easily understood, even by those unfamiliar with domain-specific terminology.
If not provided, the name should be used for display (except for Tool,
where annotations.title should be given precedence over using name,
if present).
The URI of this resource.
A description of what this resource represents.
This can be used by clients to improve the LLM's understanding of available resources. It can be thought of like a "hint" to the model.
The MIME type of this resource, if known.
Optional annotations for the client.
The size of the raw resource content, in bytes (i.e., before base64 encoding or any tokenization), if known.
This can be used by Hosts to display file sizes and estimate context window usage.
Sent from the client to the server, to read a specific resource URI.
\{
"jsonrpc": "2.0",
"id": "read-resource-example",
"method": "resources/read",
"params": \{
"\_meta": \{
"io.modelcontextprotocol/protocolVersion": "2026-07-28",
"io.modelcontextprotocol/clientInfo": \{
"name": "ExampleClient",
"version": "1.0.0"
},
"io.modelcontextprotocol/clientCapabilities": \{}
},
"uri": "file:///project/src/main.rs"
}
} Parameters for a resources/read request.
The URI of the resource. The URI can use any protocol; it is up to the server how to interpret it.
A successful response from the server for a resources/read request.
\{
"jsonrpc": "2.0",
"id": "read-resource-example",
"result": \{
"resultType": "complete",
"contents": \[
\{
"uri": "file:///project/src/main.rs",
"mimeType": "text/x-rust",
"text": "fn main() \{\n println!(\\"Hello world!\\");\n}"
}
]
}
} \{
"jsonrpc": "2.0",
"id": "read-resource-with-ttl-example",
"result": \{
"resultType": "complete",
"contents": \[
\{
"uri": "file:///project/src/main.rs",
"mimeType": "text/x-rust",
"text": "fn main() \{\n println!(\\"Hello world!\\");\n}"
}
],
"ttlMs": 60000,
"cacheScope": "private"
}
} The result returned by the server for a resources/read request.
Indicates the type of the result, which allows the client to determine how to parse the result object.
Servers implementing this protocol version MUST include this field.
For backward compatibility, when a client receives a result from a
server implementing an earlier protocol version (which does not include resultType), the client MUST treat the absent field as "complete".
A hint from the server indicating how long (in milliseconds) the client MAY cache this response before re-fetching. Semantics are analogous to HTTP Cache-Control max-age.
Indicates the intended scope of the cached response, analogous to HTTP Cache-Control: public vs Cache-Control: private.
"public": Any client or intermediary (e.g., shared gateway, proxy)
MAY cache the response and serve it to any user."private": Only the requesting user's client MAY cache the response.
Shared caches (e.g., multi-tenant gateways) MUST NOT serve a cached
copy to a different user.Sent from the client to request a list of resource templates the server has.
\{
"jsonrpc": "2.0",
"id": "list-resource-templates-example",
"method": "resources/templates/list",
"params": \{
"\_meta": \{
"io.modelcontextprotocol/protocolVersion": "2026-07-28",
"io.modelcontextprotocol/clientInfo": \{
"name": "ExampleClient",
"version": "1.0.0"
},
"io.modelcontextprotocol/clientCapabilities": \{}
}
}
} A successful response from the server for a resources/templates/list request.
\{
"jsonrpc": "2.0",
"id": "list-resource-templates-example",
"result": \{
"resultType": "complete",
"resourceTemplates": \[
\{
"uriTemplate": "file:///\{path}",
"name": "Project Files",
"title": "Project Files",
"description": "Access files in the project directory",
"mimeType": "application/octet-stream",
"icons": \[
\{
"src": "[https://example.com/folder-icon.png](https://example.com/folder-icon.png)",
"mimeType": "image/png",
"sizes": \["48x48"]
}
]
}
],
"ttlMs": 3600000,
"cacheScope": "public"
}
} The result returned by the server for a resources/templates/list request.
\{
"resultType": "complete",
"resourceTemplates": \[
\{
"uriTemplate": "file:///\{path}",
"name": "Project Files",
"title": "📁 Project Files",
"description": "Access files in the project directory",
"mimeType": "application/octet-stream",
"icons": \[
\{
"src": "[https://example.com/folder-icon.png](https://example.com/folder-icon.png)",
"mimeType": "image/png",
"sizes": \["48x48"]
}
]
}
],
"nextCursor": "next-page-cursor",
"ttlMs": 3600000,
"cacheScope": "public"
} Indicates the type of the result, which allows the client to determine how to parse the result object.
Servers implementing this protocol version MUST include this field.
For backward compatibility, when a client receives a result from a
server implementing an earlier protocol version (which does not include resultType), the client MUST treat the absent field as "complete".
An opaque token representing the pagination position after the last returned result. If present, there may be more results available.
A hint from the server indicating how long (in milliseconds) the client MAY cache this response before re-fetching. Semantics are analogous to HTTP Cache-Control max-age.
Indicates the intended scope of the cached response, analogous to HTTP Cache-Control: public vs Cache-Control: private.
"public": Any client or intermediary (e.g., shared gateway, proxy)
MAY cache the response and serve it to any user."private": Only the requesting user's client MAY cache the response.
Shared caches (e.g., multi-tenant gateways) MUST NOT serve a cached
copy to a different user.A template description for resources available on the server.
Optional set of sized icons that the client can display in a user interface.
Clients that support rendering icons MUST support at least the following MIME types:
image/png - PNG images (safe, universal compatibility)image/jpeg (and image/jpg) - JPEG images (safe, universal compatibility)Clients that support rendering icons SHOULD also support:
image/svg+xml - SVG images (scalable but requires security precautions)image/webp - WebP images (modern, efficient format)Intended for programmatic or logical use, but used as a display name in past specs or fallback (if title isn't present).
Intended for UI and end-user contexts — optimized to be human-readable and easily understood, even by those unfamiliar with domain-specific terminology.
If not provided, the name should be used for display (except for Tool,
where annotations.title should be given precedence over using name,
if present).
A URI template (according to RFC 6570) that can be used to construct resource URIs.
A description of what this template is for.
This can be used by clients to improve the LLM's understanding of available resources. It can be thought of like a "hint" to the model.
The MIME type for all resources that match this template. This should only be included if all resources matching this template have the same type.
Optional annotations for the client.
Sent from the server to request a list of root URIs from the client. Roots allow servers to ask for specific directories or files to operate on. A common example for roots is providing a set of repositories or directories a server should operate on.
This request is typically used when the server needs to understand the file system structure or access specific locations that the client has permission to read from.
Deprecated as of protocol version 2026-07-28 (SEP-2577). Remains in the specification for at least twelve months; see the deprecated features registry.
The result returned by the client for a roots/list request. This result contains an array of Root objects, each representing a root directory or file that the server can operate on.
\{
"roots": \[
\{
"uri": "file:///home/user/projects/myproject",
"name": "My Project"
}
]
} \{
"roots": \[
\{
"uri": "file:///home/user/repos/frontend",
"name": "Frontend Repository"
},
\{
"uri": "file:///home/user/repos/backend",
"name": "Backend Repository"
}
]
} Deprecated as of protocol version 2026-07-28 (SEP-2577). Remains in the specification for at least twelve months; see the deprecated features registry.
Represents a root directory or file that the server can operate on.
\{
"uri": "file:///home/user/projects/myproject",
"name": "My Project"
} Deprecated as of protocol version 2026-07-28 (SEP-2577). Remains in the specification for at least twelve months; see the deprecated features registry.
The URI identifying the root. This must start with file:// for now.
This restriction may be relaxed in future versions of the protocol to allow
other URI schemes.
An optional name for the root. This can be used to provide a human-readable identifier for the root, which may be useful for display purposes or for referencing the root in other parts of the application.
A request from the server to sample an LLM via the client. The client has full discretion over which model to select. The client should also inform the user before beginning sampling, to allow them to inspect the request (human in the loop) and decide whether to approve it.
\{
"method": "sampling/createMessage",
"params": \{
"messages": \[
\{
"role": "user",
"content": \{
"type": "text",
"text": "What is the capital of France?"
}
}
],
"modelPreferences": \{
"hints": \[
\{
"name": "claude-3-sonnet"
}
],
"intelligencePriority": 0.8,
"speedPriority": 0.5
},
"systemPrompt": "You are a helpful assistant.",
"maxTokens": 100
}
} Deprecated as of protocol version 2026-07-28 (SEP-2577). Remains in the specification for at least twelve months; see the deprecated features registry.
Parameters for a sampling/createMessage request.
\{
"messages": \[
\{
"role": "user",
"content": \{
"type": "text",
"text": "What is the capital of France?"
}
}
],
"modelPreferences": \{
"hints": \[
\{
"name": "claude-3-sonnet"
}
],
"intelligencePriority": 0.8,
"speedPriority": 0.5
},
"systemPrompt": "You are a helpful assistant.",
"maxTokens": 100
} \{
"messages": \[
\{
"role": "user",
"content": \{
"type": "text",
"text": "What's the weather like in Paris and London?"
}
}
],
"tools": \[
\{
"name": "get\_weather",
"description": "Get current weather for a city",
"inputSchema": \{
"type": "object",
"properties": \{
"city": \{
"type": "string",
"description": "City name"
}
},
"required": \["city"]
}
}
],
"toolChoice": \{
"mode": "auto"
},
"maxTokens": 1000
} \{
"messages": \[
\{
"role": "user",
"content": \{
"type": "text",
"text": "What's the weather like in Paris and London?"
}
},
\{
"role": "assistant",
"content": \[
\{
"type": "tool\_use",
"id": "call\_abc123",
"name": "get\_weather",
"input": \{ "city": "Paris" }
},
\{
"type": "tool\_use",
"id": "call\_def456",
"name": "get\_weather",
"input": \{ "city": "London" }
}
]
},
\{
"role": "user",
"content": \[
\{
"type": "tool\_result",
"toolUseId": "call\_abc123",
"content": \[
\{
"type": "text",
"text": "Weather in Paris: 18°C, partly cloudy"
}
]
},
\{
"type": "tool\_result",
"toolUseId": "call\_def456",
"content": \[
\{
"type": "text",
"text": "Weather in London: 15°C, rainy"
}
]
}
]
}
],
"tools": \[
\{
"name": "get\_weather",
"description": "Get current weather for a city",
"inputSchema": \{
"type": "object",
"properties": \{
"city": \{ "type": "string" }
},
"required": \["city"]
}
}
],
"maxTokens": 1000
} Deprecated as of protocol version 2026-07-28 (SEP-2577). Remains in the specification for at least twelve months; see the deprecated features registry.
The server's preferences for which model to select. The client MAY ignore these preferences.
An optional system prompt the server wants to use for sampling. The client MAY modify or omit this prompt.
A request to include context from one or more MCP servers (including the caller), to be attached to the prompt. The client MAY ignore this request.
Default is "none". The values "thisServer" and "allServers" are deprecated (SEP-2596): servers SHOULD
omit this field or use "none", and SHOULD only use the deprecated values if the client declares ClientCapabilities.sampling.context.
The "thisServer" and "allServers" values are deprecated as of protocol version 2025-11-25
(SEP-2596) and will be removed no later than the Sampling feature itself (SEP-2577). Omit this field or use "none".
The requested maximum number of tokens to sample (to prevent runaway completions).
The client MAY choose to sample fewer tokens than the requested maximum.
Optional metadata to pass through to the LLM provider. The format of this metadata is provider-specific.
Tools that the model may use during generation. The client MUST return an error if this field is provided but ClientCapabilities.sampling.tools is not declared.
Controls how the model uses tools.
The client MUST return an error if this field is provided but ClientCapabilities.sampling.tools is not declared.
Default is \{ mode: "auto" }.
The result returned by the client for a sampling/createMessage request. The client should inform the user before returning the sampled message, to allow them to inspect the response (human in the loop) and decide whether to allow the server to see it.
\{
"role": "assistant",
"content": \{
"type": "text",
"text": "The capital of France is Paris."
},
"model": "claude-3-sonnet-20240307",
"stopReason": "endTurn"
} \{
"role": "assistant",
"content": \[
\{
"type": "tool\_use",
"id": "call\_abc123",
"name": "get\_weather",
"input": \{
"city": "Paris"
}
},
\{
"type": "tool\_use",
"id": "call\_def456",
"name": "get\_weather",
"input": \{
"city": "London"
}
}
],
"model": "claude-3-sonnet-20240307",
"stopReason": "toolUse"
} \{
"role": "assistant",
"content": \{
"type": "text",
"text": "Based on the current weather data:\n\n- \*\*Paris\*\*: 18°C and partly cloudy - quite pleasant!\n- \*\*London\*\*: 15°C and rainy - you'll want an umbrella.\n\nParis has slightly warmer and drier conditions today."
},
"model": "claude-3-sonnet-20240307",
"stopReason": "endTurn"
} Deprecated as of protocol version 2026-07-28 (SEP-2577). Remains in the specification for at least twelve months; see the deprecated features registry.
The name of the model that generated the message.
The reason why sampling stopped, if known.
Standard values:
"endTurn": Natural end of the assistant's turn"stopSequence": A stop sequence was encountered"maxTokens": Maximum token limit was reached"toolUse": The model wants to use one or more toolsThis field is an open string to allow for provider-specific stop reasons.
Hints to use for model selection.
Keys not declared here are currently left unspecified by the spec and are up to the client to interpret.
Deprecated as of protocol version 2026-07-28 (SEP-2577). Remains in the specification for at least twelve months; see the deprecated features registry.
A hint for a model name.
The client SHOULD treat this as a substring of a model name; for example:
claude-3-5-sonnet should match claude-3-5-sonnet-20241022sonnet should match claude-3-5-sonnet-20241022, claude-3-sonnet-20240229, etc.claude should match any Claude modelThe client MAY also map the string to a different provider's model name or a different model family, as long as it fills a similar niche; for example:
gemini-1.5-flash could match claude-3-haiku-20240307The server's preferences for model selection, requested of the client during sampling.
Because LLMs can vary along multiple dimensions, choosing the "best" model is rarely straightforward. Different models excel in different areas—some are faster but less capable, others are more capable but more expensive, and so on. This interface allows servers to express their priorities across multiple dimensions to help clients make an appropriate selection for their use case.
These preferences are always advisory. The client MAY ignore them. It is also up to the client to decide how to interpret these preferences and how to balance them against other considerations.
\{
"hints": \[
\{ "name": "claude-3-sonnet" },
\{ "name": "claude" }
],
"costPriority": 0.3,
"speedPriority": 0.8,
"intelligencePriority": 0.5
} Deprecated as of protocol version 2026-07-28 (SEP-2577). Remains in the specification for at least twelve months; see the deprecated features registry.
Optional hints to use for model selection.
If multiple hints are specified, the client MUST evaluate them in order (such that the first match is taken).
The client SHOULD prioritize these hints over the numeric priorities, but MAY still use the priorities to select from ambiguous matches.
How much to prioritize cost when selecting a model. A value of 0 means cost is not important, while a value of 1 means cost is the most important factor.
How much to prioritize sampling speed (latency) when selecting a model. A value of 0 means speed is not important, while a value of 1 means speed is the most important factor.
How much to prioritize intelligence and capabilities when selecting a model. A value of 0 means intelligence is not important, while a value of 1 means intelligence is the most important factor.
Describes a message issued to or received from an LLM API.
\{
"role": "user",
"content": \{
"type": "text",
"text": "What is the capital of France?"
}
} \{
"role": "user",
"content": \[
\{
"type": "tool\_result",
"toolUseId": "call\_123",
"content": \[\{ "type": "text", "text": "Result 1" }]
},
\{
"type": "tool\_result",
"toolUseId": "call\_456",
"content": \[\{ "type": "text", "text": "Result 2" }]
}
]
} Deprecated as of protocol version 2026-07-28 (SEP-2577). Remains in the specification for at least twelve months; see the deprecated features registry.
Deprecated as of protocol version 2026-07-28 (SEP-2577). Remains in the specification for at least twelve months; see the deprecated features registry.
Controls tool selection behavior for sampling requests.
Deprecated as of protocol version 2026-07-28 (SEP-2577). Remains in the specification for at least twelve months; see the deprecated features registry.
Controls the tool use ability of the model:
"auto": Model decides whether to use tools (default)"required": Model MUST use at least one tool before completing"none": Model MUST NOT use any toolsThe result of a tool use, provided by the user back to the assistant.
\{
"type": "tool\_result",
"toolUseId": "call\_abc123",
"content": \[
\{
"type": "text",
"text": "Weather in Paris: 18°C, partly cloudy"
}
]
} Deprecated as of protocol version 2026-07-28 (SEP-2577). Remains in the specification for at least twelve months; see the deprecated features registry.
The ID of the tool use this result corresponds to.
This MUST match the ID from a previous ToolUseContent.
The unstructured result content of the tool use.
This has the same format as CallToolResult.content and can include text, images, audio, resource links, and embedded resources.
An optional structured result value.
This can be any JSON value (object, array, string, number, boolean, or null). If the tool defined an Tool.outputSchema, this SHOULD conform to that schema.
Whether the tool use resulted in an error.
If true, the content typically describes the error that occurred. Default: false
Optional metadata about the tool result. Clients SHOULD preserve this field when including tool results in subsequent sampling requests to enable caching optimizations.
A request from the assistant to call a tool.
\{
"type": "tool\_use",
"id": "call\_abc123",
"name": "get\_weather",
"input": \{
"city": "Paris"
}
} Deprecated as of protocol version 2026-07-28 (SEP-2577). Remains in the specification for at least twelve months; see the deprecated features registry.
A unique identifier for this tool use.
This ID is used to match tool results to their corresponding tool uses.
The name of the tool to call.
The arguments to pass to the tool, conforming to the tool's input schema.
Optional metadata about the tool use. Clients SHOULD preserve this field when including tool uses in subsequent sampling requests to enable caching optimizations.
A request from the client asking the server to advertise its supported
protocol versions, capabilities, and other metadata. Servers MUST
implement server/discover. Clients MAY call it but are not required
to — version negotiation can also happen inline via per-request \_meta.
\{
"jsonrpc": "2.0",
"id": "discover-1",
"method": "server/discover",
"params": \{
"\_meta": \{
"io.modelcontextprotocol/protocolVersion": "2026-07-28",
"io.modelcontextprotocol/clientInfo": \{
"name": "ExampleClient",
"version": "1.0.0"
},
"io.modelcontextprotocol/clientCapabilities": \{}
}
}
} A successful response from the server for a server/discover request.
\{
"jsonrpc": "2.0",
"id": "discover-1",
"result": \{
"resultType": "complete",
"supportedVersions": \["2026-07-28"],
"capabilities": \{
"tools": \{},
"resources": \{}
},
"serverInfo": \{
"name": "ExampleServer",
"version": "1.0.0"
},
"ttlMs": 3600000,
"cacheScope": "public"
}
} The result returned by the server for a server/discover request.
\{
"resultType": "complete",
"supportedVersions": \["2026-07-28"],
"capabilities": \{
"tools": \{},
"resources": \{}
},
"serverInfo": \{
"name": "ExampleServer",
"version": "1.0.0"
},
"instructions": "This server provides weather and resource utilities. Prefer \`get\_weather\` for forecast lookups.",
"ttlMs": 3600000,
"cacheScope": "public"
} Indicates the type of the result, which allows the client to determine how to parse the result object.
Servers implementing this protocol version MUST include this field.
For backward compatibility, when a client receives a result from a
server implementing an earlier protocol version (which does not include resultType), the client MUST treat the absent field as "complete".
MCP Protocol Versions this server supports. The client should choose a version from this list for use in subsequent requests.
The capabilities of the server.
Information about the server software implementation.
Natural-language guidance describing the server and its features.
This can be used by clients to improve an LLM's understanding of available tools (e.g., by including it in a system prompt). It should focus on information that helps the model use the server effectively and should not duplicate information already in tool descriptions.
A hint from the server indicating how long (in milliseconds) the client MAY cache this response before re-fetching. Semantics are analogous to HTTP Cache-Control max-age.
Indicates the intended scope of the cached response, analogous to HTTP Cache-Control: public vs Cache-Control: private.
"public": Any client or intermediary (e.g., shared gateway, proxy)
MAY cache the response and serve it to any user."private": Only the requesting user's client MAY cache the response.
Shared caches (e.g., multi-tenant gateways) MUST NOT serve a cached
copy to a different user.Capabilities a client may support. Known capabilities are defined here, in this schema, but this is not a closed set: any client can define its own, additional capabilities.
Experimental, non-standard capabilities that the client supports.
Present if the client supports listing roots.
Present if the client supports sampling from an LLM.
Whether the client supports context inclusion via includeContext parameter.
If not declared, servers SHOULD only use includeContext: "none" (or omit it).
Whether the client supports tool use via tools and toolChoice parameters.
Deprecated as of protocol version 2026-07-28 (SEP-2577). Remains in the specification for at least twelve months; see the deprecated features registry.
Present if the client supports elicitation from the server.
Optional MCP extensions that the client supports. Keys are extension identifiers (e.g., "io.modelcontextprotocol/oauth-client-credentials"), and values are per-extension settings objects. An empty object indicates support with no settings.
Keys MUST follow the \_meta key naming rules, with a
mandatory prefix.
Describes the MCP implementation.
Optional set of sized icons that the client can display in a user interface.
Clients that support rendering icons MUST support at least the following MIME types:
image/png - PNG images (safe, universal compatibility)image/jpeg (and image/jpg) - JPEG images (safe, universal compatibility)Clients that support rendering icons SHOULD also support:
image/svg+xml - SVG images (scalable but requires security precautions)image/webp - WebP images (modern, efficient format)Intended for programmatic or logical use, but used as a display name in past specs or fallback (if title isn't present).
Intended for UI and end-user contexts — optimized to be human-readable and easily understood, even by those unfamiliar with domain-specific terminology.
If not provided, the name should be used for display (except for Tool,
where annotations.title should be given precedence over using name,
if present).
The version of this implementation.
An optional human-readable description of what this implementation does.
This can be used by clients or servers to provide context about their purpose and capabilities. For example, a server might describe the types of resources or tools it provides, while a client might describe its intended use case.
An optional URL of the website for this implementation.
Capabilities that a server may support. Known capabilities are defined here, in this schema, but this is not a closed set: any server can define its own, additional capabilities.
Experimental, non-standard capabilities that the server supports.
Present if the server supports sending log messages to the client.
Present if the server supports argument autocompletion suggestions.
Present if the server offers any prompt templates.
OptionallistChanged?: booleanWhether this server supports notifications for changes to the prompt list.
Present if the server offers any resources to read.
Optionalsubscribe?: booleanWhether this server supports subscribing to resource updates.
OptionallistChanged?: booleanWhether this server supports notifications for changes to the resource list.
Present if the server offers any tools to call.
OptionallistChanged?: booleanWhether this server supports notifications for changes to the tool list.
Optional MCP extensions that the server supports. Keys are extension identifiers (e.g., "io.modelcontextprotocol/tasks"), and values are per-extension settings objects. An empty object indicates support with no settings.
Keys MUST follow the \_meta key naming rules, with a
mandatory prefix.
Sent from the client to open a long-lived channel for receiving notifications outside the context of a specific request. Replaces the previous HTTP GET endpoint and ensures consistent behavior between HTTP and STDIO.
\{
"jsonrpc": "2.0",
"id": "listen-1",
"method": "subscriptions/listen",
"params": \{
"\_meta": \{
"io.modelcontextprotocol/protocolVersion": "2026-07-28",
"io.modelcontextprotocol/clientInfo": \{
"name": "ExampleClient",
"version": "1.0.0"
},
"io.modelcontextprotocol/clientCapabilities": \{}
},
"notifications": \{
"toolsListChanged": true,
"resourceSubscriptions": \["file:///project/config.json"]
}
}
} Parameters for a subscriptions/listen request.
The notifications the client opts in to on this stream. The server MUST NOT send notification types the client has not explicitly requested.
The set of notification types a client may opt in to on a subscriptions/listen request.
Each notification type is opt-in; the server MUST NOT send notification types the client has not explicitly requested here.
If true, receive notifications/tools/list\_changed.
If true, receive notifications/prompts/list\_changed.
If true, receive notifications/resources/list\_changed.
Subscribe to notifications/resources/updated for these resource URIs.
Replaces the former resources/subscribe RPC.
Used by the client to invoke a tool provided by the server.
\{
"jsonrpc": "2.0",
"id": "call-tool-example",
"method": "tools/call",
"params": \{
"\_meta": \{
"io.modelcontextprotocol/protocolVersion": "2026-07-28",
"io.modelcontextprotocol/clientInfo": \{
"name": "ExampleClient",
"version": "1.0.0"
},
"io.modelcontextprotocol/clientCapabilities": \{}
},
"name": "get\_weather",
"arguments": \{
"location": "New York"
}
}
} Parameters for a tools/call request.
\{
"\_meta": \{
"io.modelcontextprotocol/protocolVersion": "2026-07-28",
"io.modelcontextprotocol/clientInfo": \{
"name": "ExampleClient",
"version": "1.0.0"
},
"io.modelcontextprotocol/clientCapabilities": \{}
},
"name": "get\_weather",
"arguments": \{
"location": "New York"
}
} \{
"\_meta": \{
"io.modelcontextprotocol/protocolVersion": "2026-07-28",
"io.modelcontextprotocol/clientInfo": \{
"name": "ExampleClient",
"version": "1.0.0"
},
"io.modelcontextprotocol/clientCapabilities": \{},
"progressToken": "oivaizmir"
},
"name": "build\_simulation",
"arguments": \{
"city": "Micropolis"
}
} The name of the tool.
Arguments to use for the tool call.
A successful response from the server for a tools/call request.
The result returned by the server for a tools/call request.
\{
"resultType": "complete",
"content": \[
\{
"type": "text",
"text": "Current weather in New York:\nTemperature: 72°F\nConditions: Partly cloudy"
}
],
"isError": false
} Indicates the type of the result, which allows the client to determine how to parse the result object.
Servers implementing this protocol version MUST include this field.
For backward compatibility, when a client receives a result from a
server implementing an earlier protocol version (which does not include resultType), the client MUST treat the absent field as "complete".
A list of content objects that represent the unstructured result of the tool call.
An optional JSON value that represents the structured result of the tool call.
This can be any JSON value (object, array, string, number, boolean, or null) that conforms to the tool's outputSchema if one is defined.
Whether the tool call ended in an error.
If not set, this is assumed to be false (the call was successful).
Any errors that originate from the tool SHOULD be reported inside the result
object, with isError set to true, not as an MCP protocol-level error
response. Otherwise, the LLM would not be able to see that an error occurred
and self-correct.
However, any errors in finding the tool, an error indicating that the server does not support tool calls, or any other exceptional conditions, should be reported as an MCP error response.
Sent from the client to request a list of tools the server has.
\{
"jsonrpc": "2.0",
"id": "list-tools-example",
"method": "tools/list",
"params": \{
"\_meta": \{
"io.modelcontextprotocol/protocolVersion": "2026-07-28",
"io.modelcontextprotocol/clientInfo": \{
"name": "ExampleClient",
"version": "1.0.0"
},
"io.modelcontextprotocol/clientCapabilities": \{}
}
}
} A successful response from the server for a tools/list request.
\{
"jsonrpc": "2.0",
"id": "list-tools-example",
"result": \{
"resultType": "complete",
"tools": \[
\{
"name": "get\_weather",
"title": "Weather Information Provider",
"description": "Get current weather information for a location",
"inputSchema": \{
"type": "object",
"properties": \{
"location": \{
"type": "string",
"description": "City name or zip code"
}
},
"required": \["location"]
},
"icons": \[
\{
"src": "[https://example.com/weather-icon.png](https://example.com/weather-icon.png)",
"mimeType": "image/png",
"sizes": \["48x48"]
}
]
}
],
"nextCursor": "next-page-cursor",
"ttlMs": 3600000,
"cacheScope": "public"
}
} The result returned by the server for a tools/list request.
\{
"resultType": "complete",
"tools": \[
\{
"name": "get\_weather",
"title": "Weather Information Provider",
"description": "Get current weather information for a location",
"inputSchema": \{
"type": "object",
"properties": \{
"location": \{
"type": "string",
"description": "City name or zip code"
}
},
"required": \["location"]
},
"icons": \[
\{
"src": "[https://example.com/weather-icon.png](https://example.com/weather-icon.png)",
"mimeType": "image/png",
"sizes": \["48x48"]
}
]
}
],
"nextCursor": "next-page-cursor",
"ttlMs": 300000,
"cacheScope": "public"
} Indicates the type of the result, which allows the client to determine how to parse the result object.
Servers implementing this protocol version MUST include this field.
For backward compatibility, when a client receives a result from a
server implementing an earlier protocol version (which does not include resultType), the client MUST treat the absent field as "complete".
An opaque token representing the pagination position after the last returned result. If present, there may be more results available.
A hint from the server indicating how long (in milliseconds) the client MAY cache this response before re-fetching. Semantics are analogous to HTTP Cache-Control max-age.
Indicates the intended scope of the cached response, analogous to HTTP Cache-Control: public vs Cache-Control: private.
"public": Any client or intermediary (e.g., shared gateway, proxy)
MAY cache the response and serve it to any user."private": Only the requesting user's client MAY cache the response.
Shared caches (e.g., multi-tenant gateways) MUST NOT serve a cached
copy to a different user.Definition for a tool the client can call.
\{
"name": "calculate\_sum",
"description": "Add two numbers",
"inputSchema": \{
"type": "object",
"properties": \{
"a": \{ "type": "number" },
"b": \{ "type": "number" }
},
"required": \["a", "b"]
}
} \{
"name": "calculate\_sum",
"description": "Add two numbers",
"inputSchema": \{
"\$schema": "[http://json-schema.org/draft-07/schema#](http://json-schema.org/draft-07/schema#)",
"type": "object",
"properties": \{
"a": \{ "type": "number" },
"b": \{ "type": "number" }
},
"required": \["a", "b"]
}
} \{
"name": "get\_current\_time",
"description": "Returns the current server time",
"inputSchema": \{
"type": "object",
"additionalProperties": false
}
} \{
"name": "get\_weather\_data",
"title": "Weather Data Retriever",
"description": "Get current weather data for a location",
"inputSchema": \{
"type": "object",
"properties": \{
"location": \{
"type": "string",
"description": "City name or zip code"
}
},
"required": \["location"]
},
"outputSchema": \{
"type": "object",
"properties": \{
"temperature": \{
"type": "number",
"description": "Temperature in celsius"
},
"conditions": \{
"type": "string",
"description": "Weather conditions description"
},
"humidity": \{
"type": "number",
"description": "Humidity percentage"
}
},
"required": \["temperature", "conditions", "humidity"]
}
} Optional set of sized icons that the client can display in a user interface.
Clients that support rendering icons MUST support at least the following MIME types:
image/png - PNG images (safe, universal compatibility)image/jpeg (and image/jpg) - JPEG images (safe, universal compatibility)Clients that support rendering icons SHOULD also support:
image/svg+xml - SVG images (scalable but requires security precautions)image/webp - WebP images (modern, efficient format)Intended for programmatic or logical use, but used as a display name in past specs or fallback (if title isn't present).
Intended for UI and end-user contexts — optimized to be human-readable and easily understood, even by those unfamiliar with domain-specific terminology.
If not provided, the name should be used for display (except for Tool,
where annotations.title should be given precedence over using name,
if present).
A human-readable description of the tool.
This can be used by clients to improve the LLM's understanding of available tools. It can be thought of like a "hint" to the model.
A JSON Schema object defining the expected parameters for the tool.
Tool arguments are always JSON objects, so type: "object" is required at the root.
Beyond that, any JSON Schema 2020-12 keyword may appear alongside type — including
composition keywords (oneOf, anyOf, allOf, not), conditional keywords
(if/then/else), reference keywords (\$ref, \$defs, \$anchor), and any other
standard validation or annotation keywords.
Defaults to JSON Schema 2020-12 when no explicit \$schema is provided.
An optional JSON Schema object defining the structure of the tool's output returned in the structuredContent field of a CallToolResult. This can be any valid JSON Schema 2020-12.
Defaults to JSON Schema 2020-12 when no explicit \$schema is provided.
Optional additional tool information.
Display name precedence order is: title, annotations.title, then name.
Additional properties describing a Tool to clients.
NOTE: all properties in ToolAnnotations are hints.
They are not guaranteed to provide a faithful description of
tool behavior (including descriptive properties like title).
Clients should never make tool use decisions based on ToolAnnotations
received from untrusted servers.
A human-readable title for the tool.
If true, the tool does not modify its environment.
Default: false
If true, the tool may perform destructive updates to its environment. If false, the tool performs only additive updates.
(This property is meaningful only when readOnlyHint == false)
Default: true
If true, calling the tool repeatedly with the same arguments will have no additional effect on its environment.
(This property is meaningful only when readOnlyHint == false)
Default: false
If true, this tool may interact with an "open world" of external entities. If false, the tool's domain of interaction is closed. For example, the world of a web search tool is open, whereas that of a memory tool is not.
Default: true
A response to a request that indicates an error occurred.