Schema Reference
Common Types
Annotations
Describes who the intended customer of this object or data is.
It can include multiple entries to indicate content useful for multiple audiences (e.g., [“user”, “assistant”]).
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.
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.
AudioContent
_meta?: { [key: string]: unknown };
annotations?: Annotations;
data: string;
mimeType: string;
type: “audio”;
}
Audio provided to or from an LLM.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
Optional annotations for the client.
The base64-encoded audio data.
The MIME type of the audio. Different providers may support different audio types.
BlobResourceContents
_meta?: { [key: string]: unknown };
blob: string;
mimeType?: string;
uri: string;
}
The contents of a specific resource or sub-resource.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
A base64-encoded string representing the binary data of the item.
The MIME type of this resource, if known.
The URI of this resource.
BooleanSchema
default?: boolean;
description?: string;
title?: string;
type: “boolean”;
}
ClientCapabilities
elicitation?: object;
experimental?: { [key: string]: object };
roots?: { listChanged?: boolean };
sampling?: object;
}
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.
Present if the client supports elicitation from the server.
Experimental, non-standard capabilities that the client supports.
Present if the client supports listing roots.
OptionallistChanged?: booleanWhether the client supports notifications for changes to the roots list.
Present if the client supports sampling from an LLM.
ContentBlock
Cursor
An opaque token used to represent a cursor for pagination.
EmbeddedResource
_meta?: { [key: string]: unknown };
annotations?: Annotations;
resource: TextResourceContents | BlobResourceContents;
type: “resource”;
}
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.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
Optional annotations for the client.
EmptyResult
A response that indicates success but carries no data.
EnumSchema
description?: string;
enum: string[];
enumNames?: string[];
title?: string;
type: “string”;
}
ImageContent
_meta?: { [key: string]: unknown };
annotations?: Annotations;
data: string;
mimeType: string;
type: “image”;
}
An image provided to or from an LLM.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
Optional annotations for the client.
The base64-encoded image data.
The MIME type of the image. Different providers may support different image types.
Implementation
Describes the name and version of an MCP implementation, with an optional title for UI representation.
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).
JSONRPCError
error: { code: number; data?: unknown; message: string };
id: RequestId;
jsonrpc: “2.0”;
}
A response to a request that indicates an error occurred.
- code: number
The error type that occurred.
Optionaldata?: unknownAdditional information about the error. The value of this member is defined by the sender (e.g. detailed error information, nested errors etc.).
- message: string
A short description of the error. The message SHOULD be limited to a concise single sentence.
JSONRPCNotification
jsonrpc: “2.0”;
method: string;
params?: { _meta?: { [key: string]: unknown }; [key: string]: unknown };
}
A notification which does not expect a response.
- [key: string]: unknown
Optional_meta?: { [key: string]: unknown }See [specification/draft/basic/index#general-fields] for notes on _meta usage.
JSONRPCRequest
id: RequestId;
jsonrpc: “2.0”;
method: string;
params?: {
_meta?: { progressToken?: ProgressToken; [key: string]: unknown };
[key: string]: unknown;
};
}
A request that expects a response.
_meta?: { progressToken?: ProgressToken; [key: string]: unknown };
[key: string]: unknown;
}
- [key: string]: unknown
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
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.
JSONRPCResponse
A successful (non-error) response to a request.
LoggingLevel
| “debug”
| “info”
| “notice”
| “warning”
| “error”
| “critical”
| “alert”
| “emergency”
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
ModelHint
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.
A hint for a model name.
The client SHOULD treat this as a substring of a model name; for example:
claude-3-5-sonnetshould matchclaude-3-5-sonnet-20241022sonnetshould matchclaude-3-5-sonnet-20241022,claude-3-sonnet-20240229, etc.claudeshould match any Claude model
The 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-flashcould matchclaude-3-haiku-20240307
ModelPreferences
costPriority?: number;
hints?: ModelHint[];
intelligencePriority?: number;
speedPriority?: number;
}
The 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.
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.
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 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.
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.
NumberSchema
description?: string;
maximum?: number;
minimum?: number;
title?: string;
type: “number” | “integer”;
}
PrimitiveSchemaDefinition
Restricted schema definitions that only allow primitive types without nested objects or arrays.
ProgressToken
A progress token, used to associate progress notifications with the original request.
Prompt
_meta?: { [key: string]: unknown };
arguments?: PromptArgument[];
description?: string;
name: string;
title?: string;
}
A prompt or prompt template that the server offers.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
A list of arguments to use for templating the prompt.
An optional description of what this prompt provides
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).
PromptArgument
Describes an argument that a prompt can accept.
A human-readable description of the argument.
Intended for programmatic or logical use, but used as a display name in past specs or fallback (if title isn’t present).
Whether this argument must be provided.
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).
PromptMessage
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.
PromptReference
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).
RequestId
A uniquely identifying ID for a request in JSON-RPC.
Resource
_meta?: { [key: string]: unknown };
annotations?: Annotations;
description?: string;
mimeType?: string;
name: string;
size?: number;
title?: string;
uri: string;
}
A known resource that the server is capable of reading.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
Optional annotations for the client.
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.
Intended for programmatic or logical use, but used as a display name in past specs or fallback (if title isn’t present).
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.
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.
ResourceContents
The contents of a specific resource or sub-resource.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
The MIME type of this resource, if known.
The URI of this resource.
ResourceLink
_meta?: { [key: string]: unknown };
annotations?: Annotations;
description?: string;
mimeType?: string;
name: string;
size?: number;
title?: string;
type: “resource_link”;
uri: string;
}
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.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
Optional annotations for the client.
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.
Intended for programmatic or logical use, but used as a display name in past specs or fallback (if title isn’t present).
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.
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.
ResourceTemplate
_meta?: { [key: string]: unknown };
annotations?: Annotations;
description?: string;
mimeType?: string;
name: string;
title?: string;
uriTemplate: string;
}
A template description for resources available on the server.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
Optional annotations for the client.
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.
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.
ResourceTemplateReference
A reference to a resource or resource template definition.
The URI or URI template of the resource.
Result
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
Role
The sender or recipient of messages and data in a conversation.
Root
Represents a root directory or file that the server can operate on.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
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.
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.
SamplingMessage
Describes a message issued to or received from an LLM API.
ServerCapabilities
completions?: object;
experimental?: { [key: string]: object };
logging?: object;
prompts?: { listChanged?: boolean };
resources?: { listChanged?: boolean; subscribe?: boolean };
tools?: { listChanged?: boolean };
}
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.
Present if the server supports argument autocompletion suggestions.
Experimental, non-standard capabilities that the server supports.
Present if the server supports sending log messages to the client.
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.
OptionallistChanged?: booleanWhether this server supports notifications for changes to the resource list.
Optionalsubscribe?: booleanWhether this server supports subscribing to resource updates.
Present if the server offers any tools to call.
OptionallistChanged?: booleanWhether this server supports notifications for changes to the tool list.
StringSchema
description?: string;
format?: “uri” | “email” | “date” | “date-time”;
maxLength?: number;
minLength?: number;
title?: string;
type: “string”;
}
TextContent
_meta?: { [key: string]: unknown };
annotations?: Annotations;
text: string;
type: “text”;
}
Text provided to or from an LLM.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
Optional annotations for the client.
The text content of the message.
TextResourceContents
_meta?: { [key: string]: unknown };
mimeType?: string;
text: string;
uri: string;
}
The contents of a specific resource or sub-resource.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
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).
The URI of this resource.
Tool
_meta?: { [key: string]: unknown };
annotations?: ToolAnnotations;
description?: string;
inputSchema: {
properties?: { [key: string]: object };
required?: string[];
type: “object”;
};
name: string;
outputSchema?: {
properties?: { [key: string]: object };
required?: string[];
type: “object”;
};
title?: string;
}
Definition for a tool the client can call.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
Optional additional tool information.
Display name precedence order is: title, annotations.title, then name.
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.
properties?: { [key: string]: object };
required?: string[];
type: “object”;
}
A JSON Schema object defining the expected parameters for the tool.
Intended for programmatic or logical use, but used as a display name in past specs or fallback (if title isn’t present).
properties?: { [key: string]: object };
required?: string[];
type: “object”;
}
An optional JSON Schema object defining the structure of the tool’s output returned in the structuredContent field of a CallToolResult.
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).
ToolAnnotations
destructiveHint?: boolean;
idempotentHint?: boolean;
openWorldHint?: boolean;
readOnlyHint?: boolean;
title?: string;
}
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.
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 the 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
If true, the tool does not modify its environment.
Default: false
A human-readable title for the tool.
completion/complete
CompleteRequest
method: “completion/complete”;
params: {
argument: { name: string; value: string };
context?: { arguments?: { [key: string]: string } };
ref: PromptReference | ResourceTemplateReference;
};
}
A request from the client to the server, to ask for completion options.
argument: { name: string; value: string };
context?: { arguments?: { [key: string]: string } };
ref: PromptReference | ResourceTemplateReference;
}
- argument: { name: string; value: string }
The argument’s information
- name: string
The name of the argument
- value: string
The value of the argument to use for completion matching.
Optionalcontext?: { arguments?: { [key: string]: string } }Additional, optional context for completions
Optionalarguments?: { [key: string]: string }Previously-resolved variables in a URI template or prompt.
CompleteResult
_meta?: { [key: string]: unknown };
completion: { hasMore?: boolean; total?: number; values: string[] };
[key: string]: unknown;
}
The server’s response to a completion/complete request
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
OptionalhasMore?: booleanIndicates whether there are additional completion options beyond those provided in the current response, even if the exact total is unknown.
Optionaltotal?: numberThe total number of completion options available. This can exceed the number of values actually sent in the response.
- values: string[]
An array of completion values. Must not exceed 100 items.
elicitation/create
ElicitRequest
method: “elicitation/create”;
params: {
message: string;
requestedSchema: {
properties: { [key: string]: PrimitiveSchemaDefinition };
required?: string[];
type: “object”;
};
};
}
A request from the server to elicit additional information from the user via the client.
message: string;
requestedSchema: {
properties: { [key: string]: PrimitiveSchemaDefinition };
required?: string[];
type: “object”;
};
}
- message: string
The message to present to the user.
- requestedSchema: {
properties: { [key: string]: PrimitiveSchemaDefinition };
required?: string[];
type: “object”;
}A restricted subset of JSON Schema. Only top-level properties are allowed, without nesting.
ElicitResult
_meta?: { [key: string]: unknown };
action: “accept” | “decline” | “cancel”;
content?: { [key: string]: string | number | boolean };
[key: string]: unknown;
}
The client’s response to an elicitation request.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
The user action in response to the elicitation.
- “accept”: User submitted the form/confirmed the action
- “decline”: User explicitly decline the action
- “cancel”: User dismissed without making an explicit choice
The submitted form data, only present when action is “accept”. Contains values matching the requested schema.
initialize
InitializeRequest
method: “initialize”;
params: {
capabilities: ClientCapabilities;
clientInfo: Implementation;
protocolVersion: string;
};
}
This request is sent from the client to the server when it first connects, asking it to begin initialization.
- protocolVersion: string
The latest version of the Model Context Protocol that the client supports. The client MAY decide to support older versions as well.
InitializeResult
_meta?: { [key: string]: unknown };
capabilities: ServerCapabilities;
instructions?: string;
protocolVersion: string;
serverInfo: Implementation;
[key: string]: unknown;
}
After receiving an initialize request from the client, the server sends this response.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
Instructions describing how to use the server and its features.
This can be used by clients to improve the LLM’s understanding of available tools, resources, etc. It can be thought of like a “hint” to the model. For example, this information MAY be added to the system prompt.
The version of the Model Context Protocol that the server wants to use. This may not match the version that the client requested. If the client cannot support this version, it MUST disconnect.
logging/setLevel
SetLevelRequest
A request from the client to the server, to enable or adjust logging.
The level of logging that the client wants to receive from the server. The server should send all logs at this level and higher (i.e., more severe) to the client as notifications/message.
notifications/cancelled
CancelledNotification
method: “notifications/cancelled”;
params: { reason?: string; requestId: RequestId };
}
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.
A client MUST NOT attempt to cancel its initialize request.
Optionalreason?: stringAn optional string describing the reason for the cancellation. This MAY be logged or presented to the user.
The ID of the request to cancel.
This MUST correspond to the ID of a request previously issued in the same direction.
notifications/initialized
InitializedNotification
method: “notifications/initialized”;
params?: { _meta?: { [key: string]: unknown }; [key: string]: unknown };
}
This notification is sent from the client to the server after initialization has finished.
- [key: string]: unknown
Optional_meta?: { [key: string]: unknown }See [specification/draft/basic/index#general-fields] for notes on _meta usage.
notifications/message
LoggingMessageNotification
method: “notifications/message”;
params: { data: unknown; level: LoggingLevel; logger?: string };
}
Notification of a log message passed from server to client. If no logging/setLevel request has been sent from the client, the server MAY decide which messages to send automatically.
- data: unknown
The data to be logged, such as a string message or an object. Any JSON serializable type is allowed here.
The severity of this log message.
Optionallogger?: stringAn optional name of the logger issuing this message.
notifications/progress
ProgressNotification
method: “notifications/progress”;
params: {
message?: string;
progress: number;
progressToken: ProgressToken;
total?: number;
};
}
An out-of-band notification used to inform the receiver of a progress update for a long-running request.
Optionalmessage?: stringAn optional message describing the current progress.
- progress: number
The progress thus far. This should increase every time progress is made, even if the total is unknown.
The progress token which was given in the initial request, used to associate this notification with the request that is proceeding.
Optionaltotal?: numberTotal number of items to process (or total progress required), if known.
notifications/prompts/list_changed
PromptListChangedNotification
method: “notifications/prompts/list_changed”;
params?: { _meta?: { [key: string]: unknown }; [key: string]: unknown };
}
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.
- [key: string]: unknown
Optional_meta?: { [key: string]: unknown }See [specification/draft/basic/index#general-fields] for notes on _meta usage.
notifications/resources/list_changed
ResourceListChangedNotification
method: “notifications/resources/list_changed”;
params?: { _meta?: { [key: string]: unknown }; [key: string]: unknown };
}
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.
- [key: string]: unknown
Optional_meta?: { [key: string]: unknown }See [specification/draft/basic/index#general-fields] for notes on _meta usage.
notifications/resources/updated
ResourceUpdatedNotification
method: “notifications/resources/updated”;
params: { uri: string };
}
A notification from the server to the client, informing it that a resource has changed and may need to be read again. This should only be sent if the client previously sent a resources/subscribe request.
- uri: string
The URI of the resource that has been updated. This might be a sub-resource of the one that the client actually subscribed to.
notifications/roots/list_changed
RootsListChangedNotification
method: “notifications/roots/list_changed”;
params?: { _meta?: { [key: string]: unknown }; [key: string]: unknown };
}
A notification from the client to the server, informing it that the list of roots has changed. This notification should be sent whenever the client adds, removes, or modifies any root. The server should then request an updated list of roots using the ListRootsRequest.
- [key: string]: unknown
Optional_meta?: { [key: string]: unknown }See [specification/draft/basic/index#general-fields] for notes on _meta usage.
notifications/tools/list_changed
ToolListChangedNotification
method: “notifications/tools/list_changed”;
params?: { _meta?: { [key: string]: unknown }; [key: string]: unknown };
}
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.
- [key: string]: unknown
Optional_meta?: { [key: string]: unknown }See [specification/draft/basic/index#general-fields] for notes on _meta usage.
ping
PingRequest
method: “ping”;
params?: {
_meta?: { progressToken?: ProgressToken; [key: string]: unknown };
[key: string]: unknown;
};
}
A ping, issued by either the server or the client, to check that the other party is still alive. The receiver must promptly respond, or else may be disconnected.
_meta?: { progressToken?: ProgressToken; [key: string]: unknown };
[key: string]: unknown;
}
- [key: string]: unknown
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
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.
prompts/get
GetPromptRequest
method: “prompts/get”;
params: { arguments?: { [key: string]: string }; name: string };
}
Used by the client to get a prompt provided by the server.
Optionalarguments?: { [key: string]: string }Arguments to use for templating the prompt.
- name: string
The name of the prompt or prompt template.
GetPromptResult
_meta?: { [key: string]: unknown };
description?: string;
messages: PromptMessage[];
[key: string]: unknown;
}
The server’s response to a prompts/get request from the client.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
An optional description for the prompt.
prompts/list
ListPromptsRequest
Sent from the client to request a list of prompts and prompt templates the server has.
Optionalcursor?: stringAn opaque token representing the current pagination position. If provided, the server should return results starting after this cursor.
ListPromptsResult
_meta?: { [key: string]: unknown };
nextCursor?: string;
prompts: Prompt[];
[key: string]: unknown;
}
The server’s response to a prompts/list request from the client.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
An opaque token representing the pagination position after the last returned result. If present, there may be more results available.
resources/list
ListResourcesRequest
Sent from the client to request a list of resources the server has.
Optionalcursor?: stringAn opaque token representing the current pagination position. If provided, the server should return results starting after this cursor.
ListResourcesResult
_meta?: { [key: string]: unknown };
nextCursor?: string;
resources: Resource[];
[key: string]: unknown;
}
The server’s response to a resources/list request from the client.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
An opaque token representing the pagination position after the last returned result. If present, there may be more results available.
resources/read
ReadResourceRequest
Sent from the client to the server, to read a specific resource URI.
- uri: string
The URI of the resource to read. The URI can use any protocol; it is up to the server how to interpret it.
ReadResourceResult
_meta?: { [key: string]: unknown };
contents: (TextResourceContents | BlobResourceContents)[];
[key: string]: unknown;
}
The server’s response to a resources/read request from the client.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
resources/subscribe
SubscribeRequest
Sent from the client to request resources/updated notifications from the server whenever a particular resource changes.
- uri: string
The URI of the resource to subscribe to. The URI can use any protocol; it is up to the server how to interpret it.
resources/templates/list
ListResourceTemplatesRequest
method: “resources/templates/list”;
params?: { cursor?: string };
}
Sent from the client to request a list of resource templates the server has.
Optionalcursor?: stringAn opaque token representing the current pagination position. If provided, the server should return results starting after this cursor.
ListResourceTemplatesResult
_meta?: { [key: string]: unknown };
nextCursor?: string;
resourceTemplates: ResourceTemplate[];
[key: string]: unknown;
}
The server’s response to a resources/templates/list request from the client.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
An opaque token representing the pagination position after the last returned result. If present, there may be more results available.
resources/unsubscribe
UnsubscribeRequest
Sent from the client to request cancellation of resources/updated notifications from the server. This should follow a previous resources/subscribe request.
- uri: string
The URI of the resource to unsubscribe from.
roots/list
ListRootsRequest
method: “roots/list”;
params?: {
_meta?: { progressToken?: ProgressToken; [key: string]: unknown };
[key: string]: unknown;
};
}
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.
_meta?: { progressToken?: ProgressToken; [key: string]: unknown };
[key: string]: unknown;
}
- [key: string]: unknown
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
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.
ListRootsResult
_meta?: { [key: string]: unknown };
roots: Root[];
[key: string]: unknown;
}
The client’s response to a roots/list request from the server. This result contains an array of Root objects, each representing a root directory or file that the server can operate on.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
sampling/createMessage
CreateMessageRequest
method: “sampling/createMessage”;
params: {
includeContext?: “none” | “thisServer” | “allServers”;
maxTokens: number;
messages: SamplingMessage[];
metadata?: object;
modelPreferences?: ModelPreferences;
stopSequences?: string[];
systemPrompt?: string;
temperature?: number;
};
}
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.
includeContext?: “none” | “thisServer” | “allServers”;
maxTokens: number;
messages: SamplingMessage[];
metadata?: object;
modelPreferences?: ModelPreferences;
stopSequences?: string[];
systemPrompt?: string;
temperature?: number;
}
OptionalincludeContext?: “none” | “thisServer” | “allServers”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.
- maxTokens: number
The maximum number of tokens to sample, as requested by the server. The client MAY choose to sample fewer tokens than requested.
Optionalmetadata?: objectOptional metadata to pass through to the LLM provider. The format of this metadata is provider-specific.
The server’s preferences for which model to select. The client MAY ignore these preferences.
OptionalstopSequences?: string[]OptionalsystemPrompt?: stringAn optional system prompt the server wants to use for sampling. The client MAY modify or omit this prompt.
Optionaltemperature?: number
CreateMessageResult
_meta?: { [key: string]: unknown };
content: TextContent | ImageContent | AudioContent;
model: string;
role: Role;
stopReason?: string;
[key: string]: unknown;
}
The client’s response to a sampling/create_message request from the server. 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.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
The name of the model that generated the message.
The reason why sampling stopped, if known.
tools/call
CallToolRequest
method: “tools/call”;
params: { arguments?: { [key: string]: unknown }; name: string };
}
Used by the client to invoke a tool provided by the server.
CallToolResult
_meta?: { [key: string]: unknown };
content: ContentBlock[];
isError?: boolean;
structuredContent?: { [key: string]: unknown };
[key: string]: unknown;
}
The server’s response to a tool call.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
A list of content objects that represent the unstructured result of the tool call.
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.
An optional JSON object that represents the structured result of the tool call.
tools/list
ListToolsRequest
Sent from the client to request a list of tools the server has.
Optionalcursor?: stringAn opaque token representing the current pagination position. If provided, the server should return results starting after this cursor.
ListToolsResult
_meta?: { [key: string]: unknown };
nextCursor?: string;
tools: Tool[];
[key: string]: unknown;
}
The server’s response to a tools/list request from the client.
See [specification/draft/basic/index#general-fields] for notes on _meta usage.
An opaque token representing the pagination position after the last returned result. If present, there may be more results available.
Optional annotations for the client. The client can use annotations to inform how objects are used or displayed