mcp

package
v0.7.0-rc.1 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: May 25, 2025 License: MIT Imports: 12 Imported by: 0

Documentation

Overview

Code generated from MCP schema. DO NOT EDIT.

Index

Constants

This section is empty.

Variables

View Source 
var (
	// ErrClientNotInitialized is returned when a client method is called before initialization
	ErrClientNotInitialized = errors.New("mcp client not initialized")

	// ErrServerNotFound is returned when trying to use a server that doesn't exist
	ErrServerNotFound = errors.New("mcp server not found")

	// ErrNoServerURLs is returned when trying to initialize without any server URLs
	ErrNoServerURLs = errors.New("no mcp server urls provided")

	// ErrNoClientsInitialized is returned when no clients could be initialized
	ErrNoClientsInitialized = errors.New("no mcp clients could be initialized")
)

Functions

This section is empty.

Types

type Annotations 

type Annotations struct {
	Audience []Role  `json:"audience"`
	Priority float64 `json:"priority"`
}

Optional annotations for the client. The client can use annotations to inform how objects are used or displayed

type AudioContent 

type AudioContent struct {
	Annotations Annotations `json:"annotations"`
	Data        string      `json:"data"`
	Mimetype    string      `json:"mimeType"`
	Type        string      `json:"type"`
}

Audio provided to or from an LLM.

type BlobResourceContents 

type BlobResourceContents struct {
	Blob     string `json:"blob"`
	Mimetype string `json:"mimeType"`
	URI      string `json:"uri"`
}

type CallToolRequest 

type CallToolRequest struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

Used by the client to invoke a tool provided by the server.

type CallToolResult 

type CallToolResult struct {
	Meta              map[string]interface{} `json:"_meta"`
	Content           []interface{}          `json:"content"`
	Iserror           bool                   `json:"isError"`
	Structuredcontent map[string]interface{} `json:"structuredContent"`
}

The server's response to a tool call.

type CancelledNotification 

type CancelledNotification struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

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.

type ClientCapabilities 

type ClientCapabilities struct {
	Experimental map[string]interface{} `json:"experimental"`
	Roots        map[string]interface{} `json:"roots"`
	Sampling     map[string]interface{} `json:"sampling"`
}

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.

type ClientNotification 

type ClientNotification struct {
}

type ClientRequest 

type ClientRequest struct {
}

type ClientResult 

type ClientResult struct {
}

type CompleteRequest 

type CompleteRequest struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

A request from the client to the server, to ask for completion options.

type CompleteResult 

type CompleteResult struct {
	Meta       map[string]interface{} `json:"_meta"`
	Completion map[string]interface{} `json:"completion"`
}

The server's response to a completion/complete request

type CreateMessageRequest 

type CreateMessageRequest struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

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.

type CreateMessageResult 

type CreateMessageResult struct {
	Meta       map[string]interface{} `json:"_meta"`
	Content    interface{}            `json:"content"`
	Model      string                 `json:"model"`
	Role       Role                   `json:"role"`
	Stopreason string                 `json:"stopReason"`
}

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.

type Cursor 

type Cursor struct {
}

An opaque token used to represent a cursor for pagination.

type EmbeddedResource 

type EmbeddedResource struct {
	Annotations Annotations `json:"annotations"`
	Resource    interface{} `json:"resource"`
	Type        string      `json:"type"`
}

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 EmptyResult 

type EmptyResult struct {
}

type GetPromptRequest 

type GetPromptRequest struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

Used by the client to get a prompt provided by the server.

type GetPromptResult 

type GetPromptResult struct {
	Meta        map[string]interface{} `json:"_meta"`
	Description string                 `json:"description"`
	Messages    []PromptMessage        `json:"messages"`
}

The server's response to a prompts/get request from the client.

type ImageContent 

type ImageContent struct {
	Annotations Annotations `json:"annotations"`
	Data        string      `json:"data"`
	Mimetype    string      `json:"mimeType"`
	Type        string      `json:"type"`
}

An image provided to or from an LLM.

type Implementation 

type Implementation struct {
	Name    string `json:"name"`
	Version string `json:"version"`
}

Describes the name and version of an MCP implementation.

type InitializeRequest 

type InitializeRequest struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

This request is sent from the client to the server when it first connects, asking it to begin initialization.

type InitializeResult 

type InitializeResult struct {
	Meta            map[string]interface{} `json:"_meta"`
	Capabilities    ServerCapabilities     `json:"capabilities"`
	Instructions    string                 `json:"instructions"`
	Protocolversion string                 `json:"protocolVersion"`
	Serverinfo      Implementation         `json:"serverInfo"`
}

After receiving an initialize request from the client, the server sends this response.

type InitializedNotification 

type InitializedNotification struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

This notification is sent from the client to the server after initialization has finished.

type JSONRPCBatchRequest 

type JSONRPCBatchRequest struct {
}

A JSON-RPC batch request, as described in https://www.jsonrpc.org/specification#batch.

type JSONRPCBatchResponse 

type JSONRPCBatchResponse struct {
}

A JSON-RPC batch response, as described in https://www.jsonrpc.org/specification#batch.

type JSONRPCError 

type JSONRPCError struct {
	Error   map[string]interface{} `json:"error"`
	ID      RequestId              `json:"id"`
	JSONRPC string                 `json:"jsonrpc"`
}

A response to a request that indicates an error occurred.

type JSONRPCMessage 

type JSONRPCMessage struct {
}

Refers to any valid JSON-RPC object that can be decoded off the wire, or encoded to be sent.

type JSONRPCNotification 

type JSONRPCNotification struct {
	JSONRPC string                 `json:"jsonrpc"`
	Method  string                 `json:"method"`
	Params  map[string]interface{} `json:"params"`
}

A notification which does not expect a response.

type JSONRPCRequest 

type JSONRPCRequest struct {
	ID      RequestId              `json:"id"`
	JSONRPC string                 `json:"jsonrpc"`
	Method  string                 `json:"method"`
	Params  map[string]interface{} `json:"params"`
}

A request that expects a response.

type JSONRPCResponse 

type JSONRPCResponse struct {
	ID      RequestId `json:"id"`
	JSONRPC string    `json:"jsonrpc"`
	Result  Result    `json:"result"`
}

A successful (non-error) response to a request.

type ListPromptsRequest 

type ListPromptsRequest struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

Sent from the client to request a list of prompts and prompt templates the server has.

type ListPromptsResult 

type ListPromptsResult struct {
	Meta       map[string]interface{} `json:"_meta"`
	Nextcursor string                 `json:"nextCursor"`
	Prompts    []Prompt               `json:"prompts"`
}

The server's response to a prompts/list request from the client.

type ListResourceTemplatesRequest 

type ListResourceTemplatesRequest struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

Sent from the client to request a list of resource templates the server has.

type ListResourceTemplatesResult 

type ListResourceTemplatesResult struct {
	Meta              map[string]interface{} `json:"_meta"`
	Nextcursor        string                 `json:"nextCursor"`
	Resourcetemplates []ResourceTemplate     `json:"resourceTemplates"`
}

The server's response to a resources/templates/list request from the client.

type ListResourcesRequest 

type ListResourcesRequest struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

Sent from the client to request a list of resources the server has.

type ListResourcesResult 

type ListResourcesResult struct {
	Meta       map[string]interface{} `json:"_meta"`
	Nextcursor string                 `json:"nextCursor"`
	Resources  []Resource             `json:"resources"`
}

The server's response to a resources/list request from the client.

type ListRootsRequest 

type ListRootsRequest struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

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.

type ListRootsResult 

type ListRootsResult struct {
	Meta  map[string]interface{} `json:"_meta"`
	Roots []Root                 `json:"roots"`
}

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.

type ListToolsRequest 

type ListToolsRequest struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

Sent from the client to request a list of tools the server has.

type ListToolsResult 

type ListToolsResult struct {
	Meta       map[string]interface{} `json:"_meta"`
	Nextcursor string                 `json:"nextCursor"`
	Tools      []Tool                 `json:"tools"`
}

The server's response to a tools/list request from the client.

type LoggingLevel 

type LoggingLevel string

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 

const (
	LoggingLevelAlert     LoggingLevel = "alert"
	LoggingLevelCritical  LoggingLevel = "critical"
	LoggingLevelDebug     LoggingLevel = "debug"
	LoggingLevelEmergency LoggingLevel = "emergency"
	LoggingLevelError     LoggingLevel = "error"
	LoggingLevelInfo      LoggingLevel = "info"
	LoggingLevelNotice    LoggingLevel = "notice"
	LoggingLevelWarning   LoggingLevel = "warning"
)

LoggingLevel enum values

type LoggingMessageNotification 

type LoggingMessageNotification struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

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.

type MCPClient 

type MCPClient struct {
	ServerURLs          []string
	Clients             map[string]*m.Client
	Logger              logger.Logger
	Config              config.Config
	ServerCapabilities  map[string]ServerCapabilities
	ServerTools         map[string][]Tool
	ChatCompletionTools []providers.ChatCompletionTool
	Initialized         bool
}

MCPClient provides methods to interact with MCP servers

func (*MCPClient) ConvertMCPToolsToChatCompletionTools 

func (mc *MCPClient) ConvertMCPToolsToChatCompletionTools(serverTools []Tool) []providers.ChatCompletionTool

ConvertMCPToolsToChatCompletionTools converts MCP server tools to chat completion tools

func (*MCPClient) ExecuteTool 

func (mc *MCPClient) ExecuteTool(ctx context.Context, request Request, serverURL string) (*CallToolResult, error)

ExecuteTool implements MCPClientInterface.

func (*MCPClient) GetAllChatCompletionTools 

func (mc *MCPClient) GetAllChatCompletionTools() []providers.ChatCompletionTool

GetAllChatCompletionTools returns all pre-converted chat completion tools from all servers

func (*MCPClient) GetServerCapabilities 

func (mc *MCPClient) GetServerCapabilities() map[string]ServerCapabilities

GetServerCapabilities implements MCPClientInterface.

func (*MCPClient) GetServerTools 

func (mc *MCPClient) GetServerTools(serverURL string) ([]Tool, error)

func (*MCPClient) GetServers 

func (mc *MCPClient) GetServers() []string

func (*MCPClient) InitializeAll 

func (mc *MCPClient) InitializeAll(ctx context.Context) error

InitializeAll implements MCPClientInterface.

func (*MCPClient) IsInitialized 

func (mc *MCPClient) IsInitialized() bool

IsInitialized implements MCPClientInterface.

func (*MCPClient) NewClient 

func (mc *MCPClient) NewClient(url string) *m.Client

NewClient creates a new MCP client for a given server URL

type MCPClientInterface 

type MCPClientInterface interface {
	// InitializeAll establishes connection with MCP servers and performs handshake
	InitializeAll(ctx context.Context) error

	// IsInitialized returns whether the client has been successfully initialized
	IsInitialized() bool

	// ExecuteTool invokes a tool on the appropriate MCP server
	ExecuteTool(ctx context.Context, request Request, serverURL string) (*CallToolResult, error)

	// GetServerCapabilities returns the server capabilities map
	GetServerCapabilities() map[string]ServerCapabilities

	// GetServers returns the list of MCP server URLs
	GetServers() []string

	// GetServerTools returns the tools available on the specified server
	GetServerTools(serverURL string) ([]Tool, error)

	// GetAllChatCompletionTools returns all pre-converted chat completion tools from all servers
	GetAllChatCompletionTools() []providers.ChatCompletionTool

	// ConvertMCPToolsToChatCompletionTools converts MCP server tools to chat completion tools
	ConvertMCPToolsToChatCompletionTools([]Tool) []providers.ChatCompletionTool
}

MCPClientInterface defines the interface for MCP client implementations

func NewMCPClient 

func NewMCPClient(serverURLs []string, logger logger.Logger, cfg config.Config) MCPClientInterface

NewMCPClient is a variable holding the function to create a new MCP client

type ModelHint 

type ModelHint struct {
	Name string `json:"name"`
}

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.

type ModelPreferences 

type ModelPreferences struct {
	Costpriority         float64     `json:"costPriority"`
	Hints                []ModelHint `json:"hints"`
	Intelligencepriority float64     `json:"intelligencePriority"`
	Speedpriority        float64     `json:"speedPriority"`
}

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.

type Notification 

type Notification struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

type PaginatedRequest 

type PaginatedRequest struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

type PaginatedResult 

type PaginatedResult struct {
	Meta       map[string]interface{} `json:"_meta"`
	Nextcursor string                 `json:"nextCursor"`
}

type PingRequest 

type PingRequest struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

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.

type ProgressNotification 

type ProgressNotification struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

An out-of-band notification used to inform the receiver of a progress update for a long-running request.

type ProgressToken 

type ProgressToken struct {
}

A progress token, used to associate progress notifications with the original request.

type Prompt 

type Prompt struct {
	Arguments   []PromptArgument `json:"arguments"`
	Description string           `json:"description"`
	Name        string           `json:"name"`
}

A prompt or prompt template that the server offers.

type PromptArgument 

type PromptArgument struct {
	Description string `json:"description"`
	Name        string `json:"name"`
	Required    bool   `json:"required"`
}

Describes an argument that a prompt can accept.

type PromptListChangedNotification 

type PromptListChangedNotification struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

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.

type PromptMessage 

type PromptMessage struct {
	Content interface{} `json:"content"`
	Role    Role        `json:"role"`
}

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.

type PromptReference 

type PromptReference struct {
	Name string `json:"name"`
	Type string `json:"type"`
}

Identifies a prompt.

type ReadResourceRequest 

type ReadResourceRequest struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

Sent from the client to the server, to read a specific resource URI.

type ReadResourceResult 

type ReadResourceResult struct {
	Meta     map[string]interface{} `json:"_meta"`
	Contents []interface{}          `json:"contents"`
}

The server's response to a resources/read request from the client.

type Request 

type Request struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

type RequestId 

type RequestId struct {
}

A uniquely identifying ID for a request in JSON-RPC.

type Resource 

type Resource struct {
	Annotations Annotations `json:"annotations"`
	Description string      `json:"description"`
	Mimetype    string      `json:"mimeType"`
	Name        string      `json:"name"`
	Size        int         `json:"size"`
	URI         string      `json:"uri"`
}

A known resource that the server is capable of reading.

type ResourceContents 

type ResourceContents struct {
	Mimetype string `json:"mimeType"`
	URI      string `json:"uri"`
}

The contents of a specific resource or sub-resource.

type ResourceListChangedNotification 

type ResourceListChangedNotification struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

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.

type ResourceReference 

type ResourceReference struct {
	Type string `json:"type"`
	URI  string `json:"uri"`
}

A reference to a resource or resource template definition.

type ResourceTemplate 

type ResourceTemplate struct {
	Annotations Annotations `json:"annotations"`
	Description string      `json:"description"`
	Mimetype    string      `json:"mimeType"`
	Name        string      `json:"name"`
	Uritemplate string      `json:"uriTemplate"`
}

A template description for resources available on the server.

type ResourceUpdatedNotification 

type ResourceUpdatedNotification struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

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.

type Result 

type Result struct {
	Meta map[string]interface{} `json:"_meta"`
}

type Role 

type Role string

The sender or recipient of messages and data in a conversation. 

const (
	RoleAssistant Role = "assistant"
	RoleUser      Role = "user"
)

Role enum values

type Root 

type Root struct {
	Name string `json:"name"`
	URI  string `json:"uri"`
}

Represents a root directory or file that the server can operate on.

type RootsListChangedNotification 

type RootsListChangedNotification struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

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.

type SamplingMessage 

type SamplingMessage struct {
	Content interface{} `json:"content"`
	Role    Role        `json:"role"`
}

Describes a message issued to or received from an LLM API.

type ServerCapabilities 

type ServerCapabilities struct {
	Completions  map[string]interface{} `json:"completions"`
	Experimental map[string]interface{} `json:"experimental"`
	Logging      map[string]interface{} `json:"logging"`
	Prompts      map[string]interface{} `json:"prompts"`
	Resources    map[string]interface{} `json:"resources"`
	Tools        map[string]interface{} `json:"tools"`
}

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.

type ServerNotification 

type ServerNotification struct {
}

type ServerRequest 

type ServerRequest struct {
}

type ServerResult 

type ServerResult struct {
}

type SetLevelRequest 

type SetLevelRequest struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

A request from the client to the server, to enable or adjust logging.

type SubscribeRequest 

type SubscribeRequest struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

Sent from the client to request resources/updated notifications from the server whenever a particular resource changes.

type TextContent 

type TextContent struct {
	Annotations Annotations `json:"annotations"`
	Text        string      `json:"text"`
	Type        string      `json:"type"`
}

Text provided to or from an LLM.

type TextResourceContents 

type TextResourceContents struct {
	Mimetype string `json:"mimeType"`
	Text     string `json:"text"`
	URI      string `json:"uri"`
}

type Tool 

type Tool struct {
	Annotations  ToolAnnotations        `json:"annotations"`
	Description  string                 `json:"description"`
	Inputschema  map[string]interface{} `json:"inputSchema"`
	Name         string                 `json:"name"`
	Outputschema map[string]interface{} `json:"outputSchema"`
}

Definition for a tool the client can call.

type ToolAnnotations 

type ToolAnnotations struct {
	Destructivehint bool   `json:"destructiveHint"`
	Idempotenthint  bool   `json:"idempotentHint"`
	Openworldhint   bool   `json:"openWorldHint"`
	Readonlyhint    bool   `json:"readOnlyHint"`
	Title           string `json:"title"`
}

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.

type ToolListChangedNotification 

type ToolListChangedNotification struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

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.

type UnsubscribeRequest 

type UnsubscribeRequest struct {
	Method string                 `json:"method"`
	Params map[string]interface{} `json:"params"`
}

Sent from the client to request cancellation of resources/updated notifications from the server. This should follow a previous resources/subscribe request.

Source Files

View all Source files

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.