Schema

Documentation Index

Fetch the complete documentation index at: https://agentclientprotocol.com/llms.txt

Use this file to discover all available pages before exploring further.

​

Agent

Defines the interface that all ACP-compliant agents must implement. Agents are programs that use generative AI to autonomously modify code. They handle requests from clients and execute tasks using language models and tools.

​

authenticate

Authenticates the client using the specified authentication method. Called when the agent requires authentication before allowing session creation. The client provides the authentication method ID that was advertised during initialization. After successful authentication, the client can proceed to create sessions with new_session without receiving an auth_required error. See protocol docs: Initialization

​

AuthenticateRequest

Request parameters for the authenticate method. Specifies which authentication method to use. Type: Object Properties:

​

AuthenticateResponse

Response to the authenticate method. Type: Object Properties:

​

document/didChange

UNSTABLE Notification sent when a file is edited.

​

DidChangeDocumentNotification

Notification sent when a file is edited. Type: Object Properties:

​

document/didClose

UNSTABLE Notification sent when a file is closed.

​

DidCloseDocumentNotification

Notification sent when a file is closed. Type: Object Properties:

​

document/didFocus

UNSTABLE Notification sent when a file becomes the active editor tab.

​

DidFocusDocumentNotification

Notification sent when a file becomes the active editor tab. Type: Object Properties:

​

document/didOpen

UNSTABLE Notification sent when a file is opened in the editor.

​

DidOpenDocumentNotification

Notification sent when a file is opened in the editor. Type: Object Properties:

​

document/didSave

UNSTABLE Notification sent when a file is saved.

​

DidSaveDocumentNotification

Notification sent when a file is saved. Type: Object Properties:

​

initialize

Establishes the connection with a client and negotiates protocol capabilities. This method is called once at the beginning of the connection to:

• Negotiate the protocol version to use
• Exchange capability information between client and agent
• Determine available authentication methods

The agent should respond with its supported protocol version and capabilities. See protocol docs: Initialization

​

InitializeRequest

Request parameters for the initialize method. Sent by the client to establish connection and negotiate capabilities. See protocol docs: Initialization Type: Object Properties:

​

InitializeResponse

Response to the initialize method. Contains the negotiated protocol version and agent capabilities. See protocol docs: Initialization Type: Object Properties:

​

logout

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Logs out of the current authenticated state. After a successful logout, all new sessions will require authentication. There is no guarantee about the behavior of already running sessions.

​

LogoutRequest

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Request parameters for the logout method. Terminates the current authenticated session. Type: Object Properties:

​

LogoutResponse

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Response to the logout method. Type: Object Properties:

​

nes/accept

UNSTABLE Notification sent when a suggestion is accepted.

​

AcceptNesNotification

Notification sent when a suggestion is accepted. Type: Object Properties:

​

nes/close

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Closes an active NES session and frees up any resources associated with it. The agent must cancel any ongoing work and then free up any resources associated with the NES session.

​

CloseNesRequest

Request to close an NES session. The agent must cancel any ongoing work related to the NES session and then free up any resources associated with the session. Type: Object Properties:

​

CloseNesResponse

Response from closing an NES session. Type: Object Properties:

​

nes/reject

UNSTABLE Notification sent when a suggestion is rejected.

​

RejectNesNotification

Notification sent when a suggestion is rejected. Type: Object Properties:

​

nes/start

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Starts an NES session.

​

StartNesRequest

Request to start an NES session. Type: Object Properties:

​

StartNesResponse

Response to nes/start. Type: Object Properties:

​

nes/suggest

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Requests a code suggestion.

​

SuggestNesRequest

Request for a code suggestion. Type: Object Properties:

​

SuggestNesResponse

Response to nes/suggest. Type: Object Properties:

​

providers/disable

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Disables a provider.

​

DisableProvidersRequest

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Request parameters for providers/disable. Type: Object Properties:

​

DisableProvidersResponse

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Response to providers/disable. Type: Object Properties:

​

providers/list

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Lists providers that can be configured by the client.

​

ListProvidersRequest

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Request parameters for providers/list. Type: Object Properties:

​

ListProvidersResponse

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Response to providers/list. Type: Object Properties:

​

providers/set

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Replaces the configuration for a provider.

​

SetProvidersRequest

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Request parameters for providers/set. Replaces the full configuration for one provider id. Type: Object Properties:

​

SetProvidersResponse

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Response to providers/set. Type: Object Properties:

​

session/cancel

Cancels ongoing operations for a session. This is a notification sent by the client to cancel an ongoing prompt turn. Upon receiving this notification, the Agent SHOULD:

• Stop all language model requests as soon as possible
• Abort all tool call invocations in progress
• Send any pending session/update notifications
• Respond to the original session/prompt request with StopReason::Cancelled

See protocol docs: Cancellation

​

CancelNotification

Notification to cancel ongoing operations for a session. See protocol docs: Cancellation Type: Object Properties:

​

session/close

Closes an active session and frees up any resources associated with it. This method is only available if the agent advertises the sessionCapabilities.close capability. The agent must cancel any ongoing work (as if session/cancel was called) and then free up any resources associated with the session.

​

CloseSessionRequest

Request parameters for closing an active session. If supported, the agent must cancel any ongoing work related to the session (treat it as if session/cancel was called) and then free up any resources associated with the session. Only available if the Agent supports the sessionCapabilities.close capability. Type: Object Properties:

​

CloseSessionResponse

Response from closing a session. Type: Object Properties:

​

session/fork

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Forks an existing session to create a new independent session. This method is only available if the agent advertises the session.fork capability. The agent should create a new session with the same conversation context as the original, allowing operations like generating summaries without affecting the original session’s history.

​

ForkSessionRequest

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Request parameters for forking an existing session. Creates a new session based on the context of an existing one, allowing operations like generating summaries without affecting the original session’s history. Only available if the Agent supports the session.fork capability. Type: Object Properties:

​

ForkSessionResponse

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Response from forking an existing session. Type: Object Properties:

​

session/list

Lists existing sessions known to the agent. This method is only available if the agent advertises the sessionCapabilities.list capability. The agent should return metadata about sessions with optional filtering and pagination support.

​

ListSessionsRequest

Request parameters for listing existing sessions. Only available if the Agent supports the sessionCapabilities.list capability. Type: Object Properties:

​

ListSessionsResponse

Response from listing sessions. Type: Object Properties:

​

session/load

Loads an existing session to resume a previous conversation. This method is only available if the agent advertises the loadSession capability. The agent should:

• Restore the session context and conversation history
• Connect to the specified MCP servers
• Stream the entire conversation history back to the client via notifications

See protocol docs: Loading Sessions

​

LoadSessionRequest

Request parameters for loading an existing session. Only available if the Agent supports the loadSession capability. See protocol docs: Loading Sessions Type: Object Properties:

​

LoadSessionResponse

Response from loading an existing session. Type: Object Properties:

​

session/new

Creates a new conversation session with the agent. Sessions represent independent conversation contexts with their own history and state. The agent should:

• Create a new session context
• Connect to any specified MCP servers
• Return a unique session ID for future requests

May return an auth_required error if the agent requires authentication. See protocol docs: Session Setup

​

NewSessionRequest

Request parameters for creating a new session. See protocol docs: Creating a Session Type: Object Properties:

​

NewSessionResponse

Response from creating a new session. See protocol docs: Creating a Session Type: Object Properties:

​

session/prompt

Processes a user prompt within a session. This method handles the whole lifecycle of a prompt:

• Receives user messages with optional context (files, images, etc.)
• Processes the prompt using language models
• Reports language model content and tool calls to the Clients
• Requests permission to run tools
• Executes any requested tool calls
• Returns when the turn is complete with a stop reason

See protocol docs: Prompt Turn

​

PromptRequest

Request parameters for sending a user prompt to the agent. Contains the user’s message and any additional context. See protocol docs: User Message Type: Object Properties:

​

PromptResponse

Response from processing a user prompt. See protocol docs: Check for Completion Type: Object Properties:

​

session/resume

Resumes an existing session without returning previous messages. This method is only available if the agent advertises the sessionCapabilities.resume capability. The agent should resume the session context, allowing the conversation to continue without replaying the message history (unlike session/load).

​

ResumeSessionRequest

Request parameters for resuming an existing session. Resumes an existing session without returning previous messages (unlike session/load). This is useful for agents that can resume sessions but don’t implement full session loading. Only available if the Agent supports the sessionCapabilities.resume capability. Type: Object Properties:

​

ResumeSessionResponse

Response from resuming an existing session. Type: Object Properties:

​

session/set_config_option

Sets the current value for a session configuration option.

​

SetSessionConfigOptionRequest

Request parameters for setting a session configuration option. Type: Union Shared properties: Variants:

​

SetSessionConfigOptionResponse

Response to session/set_config_option method. Type: Object Properties:

​

session/set_mode

Sets the current mode for a session. Allows switching between different agent modes (e.g., “ask”, “architect”, “code”) that affect system prompts, tool availability, and permission behaviors. The mode must be one of the modes advertised in availableModes during session creation or loading. Agents may also change modes autonomously and notify the client via current_mode_update notifications. This method can be called at any time during a session, whether the Agent is idle or actively generating a response. See protocol docs: Session Modes

​

SetSessionModeRequest

Request parameters for setting a session mode. Type: Object Properties:

​

SetSessionModeResponse

Response to session/set_mode method. Type: Object Properties:

​

session/set_model

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Select a model for a given session.

​

SetSessionModelRequest

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Request parameters for setting a session model. Type: Object Properties:

​

SetSessionModelResponse

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Response to session/set_model method. Type: Object Properties:

​

Client

Defines the interface that ACP-compliant clients must implement. Clients are typically code editors (IDEs, text editors) that provide the interface between users and AI agents. They manage the environment, handle user interactions, and control access to resources.

​

elicitation/complete

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Notification that a URL-based elicitation has completed.

​

CompleteElicitationNotification

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Notification sent by the agent when a URL-based elicitation is complete. Type: Object Properties:

​

elicitation/create

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Requests structured user input via a form or URL.

​

CreateElicitationRequest

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Request from the agent to elicit structured user input. The agent sends this to the client to request information from the user, either via a form or by directing them to a URL. Elicitations are tied to a session (optionally a tool call) or a request. Type: Union Shared properties: Variants:

​

CreateElicitationResponse

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Response from the client to an elicitation request. Type: Union Shared properties: Variants:

​

fs/read_text_file

Reads content from a text file in the client’s file system. Only available if the client advertises the fs.readTextFile capability. Allows the agent to access file contents within the client’s environment. See protocol docs: Client

​

ReadTextFileRequest

Request to read content from a text file. Only available if the client supports the fs.readTextFile capability. Type: Object Properties:

​

ReadTextFileResponse

Response containing the contents of a text file. Type: Object Properties:

​

fs/write_text_file

Writes content to a text file in the client’s file system. Only available if the client advertises the fs.writeTextFile capability. Allows the agent to create or modify files within the client’s environment. See protocol docs: Client

​

WriteTextFileRequest

Request to write content to a text file. Only available if the client supports the fs.writeTextFile capability. Type: Object Properties:

​

WriteTextFileResponse

Response to fs/write_text_file Type: Object Properties:

​

session/request_permission

Requests permission from the user for a tool call operation. Called by the agent when it needs user authorization before executing a potentially sensitive operation. The client should present the options to the user and return their decision. If the client cancels the prompt turn via session/cancel, it MUST respond to this request with RequestPermissionOutcome::Cancelled. See protocol docs: Requesting Permission

​

RequestPermissionRequest

Request for user permission to execute a tool call. Sent when the agent needs authorization before performing a sensitive operation. See protocol docs: Requesting Permission Type: Object Properties:

​

RequestPermissionResponse

Response to a permission request. Type: Object Properties:

​

session/update

Handles session update notifications from the agent. This is a notification endpoint (no response expected) that receives real-time updates about session progress, including message chunks, tool calls, and execution plans. Note: Clients SHOULD continue accepting tool call updates even after sending a session/cancel notification, as the agent may send final updates before responding with the cancelled stop reason. See protocol docs: Agent Reports Output

​

SessionNotification

Notification containing a session update from the agent. Used to stream real-time progress and results during prompt processing. See protocol docs: Agent Reports Output Type: Object Properties:

​

terminal/create

Executes a command in a new terminal Only available if the terminal Client capability is set to true. Returns a TerminalId that can be used with other terminal methods to get the current output, wait for exit, and kill the command. The TerminalId can also be used to embed the terminal in a tool call by using the ToolCallContent::Terminal variant. The Agent is responsible for releasing the terminal by using the terminal/release method. See protocol docs: Terminals

​

CreateTerminalRequest

Request to create a new terminal and execute a command. Type: Object Properties:

​

CreateTerminalResponse

Response containing the ID of the created terminal. Type: Object Properties:

​

terminal/kill

Kills the terminal command without releasing the terminal While terminal/release will also kill the command, this method will keep the TerminalId valid so it can be used with other methods. This method can be helpful when implementing command timeouts which terminate the command as soon as elapsed, and then get the final output so it can be sent to the model. Note: Call terminal/release when TerminalId is no longer needed. See protocol docs: Terminals

​

KillTerminalRequest

Request to kill a terminal without releasing it. Type: Object Properties:

​

KillTerminalResponse

Response to terminal/kill method Type: Object Properties:

​

terminal/output

Gets the terminal output and exit status Returns the current content in the terminal without waiting for the command to exit. If the command has already exited, the exit status is included. See protocol docs: Terminals

​

TerminalOutputRequest

Request to get the current output and status of a terminal. Type: Object Properties:

​

TerminalOutputResponse

Response containing the terminal output and exit status. Type: Object Properties:

​

terminal/release

Releases a terminal The command is killed if it hasn’t exited yet. Use terminal/wait_for_exit to wait for the command to exit before releasing the terminal. After release, the TerminalId can no longer be used with other terminal/* methods, but tool calls that already contain it, continue to display its output. The terminal/kill method can be used to terminate the command without releasing the terminal, allowing the Agent to call terminal/output and other methods. See protocol docs: Terminals

​

ReleaseTerminalRequest

Request to release a terminal and free its resources. Type: Object Properties:

​

ReleaseTerminalResponse

Response to terminal/release method Type: Object Properties:

​

terminal/wait_for_exit

Waits for the terminal command to exit and return its exit status See protocol docs: Terminals

​

WaitForTerminalExitRequest

Request to wait for a terminal command to exit. Type: Object Properties:

​

WaitForTerminalExitResponse

Response containing the exit status of a terminal command. Type: Object Properties:

​

Protocol Level

Defines the interface that ACP-compliant agents and clients must both implement. Notifications whose methods start with ‘$/' are messages which are protocol implementation dependent and might not be implementable in all clients or agents. For example if the implementation uses a single threaded synchronous programming language then there is little it can do to react to a `$/cancel_request` notification. If an agent or client receives notifications starting with ’$/’ it is free to ignore the notification.

​

$/cancel_request

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Cancels an ongoing request. This is a notification sent by the side that sent a request to cancel that request. Upon receiving this notification, the receiver:

1. MUST cancel the corresponding request activity and all nested activities
2. MAY send any pending notifications.
3. MUST send one of these responses for the original request:

• Valid response with appropriate data (partial results or cancellation marker)
• Error response with code -32800 (Cancelled)

See protocol docs: Cancellation

​

CancelRequestNotification

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Notification to cancel an ongoing request. See protocol docs: Cancellation Type: Object Properties:

​

AgentAuthCapabilities

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Authentication-related capabilities supported by the agent. Type: Object Properties:

​

AgentCapabilities

Capabilities supported by the agent. Advertised during initialization to inform the client about available features and content types. See protocol docs: Agent Capabilities Type: Object Properties:

​

Annotations

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

​

AudioContent

Audio provided to or from an LLM. Type: Object Properties:

​

AuthCapabilities

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Authentication capabilities supported by the client. Advertised during initialization to inform the agent which authentication method types the client can handle. This governs opt-in types that require additional client-side support. Type: Object Properties:

​

AuthEnvVar

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Describes a single environment variable for an AuthMethodEnvVar authentication method. Type: Object Properties:

​

AuthMethod

Describes an available authentication method. The type field acts as the discriminator in the serialized JSON form. When no type is present, the method is treated as agent. Type: Union

​

AuthMethodAgent

Agent handles authentication itself. This is the default authentication method type. Type: Object Properties:

​

AuthMethodEnvVar

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Environment variable authentication method. The user provides credentials that the client passes to the agent as environment variables. Type: Object Properties:

​

AuthMethodTerminal

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Terminal-based authentication method. The client runs an interactive terminal for the user to authenticate via a TUI. Type: Object Properties:

​

AvailableCommand

Information about a command. Type: Object Properties:

​

AvailableCommandInput

The input specification for a command. All text that was typed after the command name is provided as input. Type: Object Properties:

​

AvailableCommandsUpdate

Available commands are ready or have changed Type: Object Properties:

​

BlobResourceContents

Binary resource contents. Type: Object Properties:

​

BooleanPropertySchema

Schema for boolean properties in an elicitation form. Type: Object Properties:

​

ClientCapabilities

Capabilities supported by the client. Advertised during initialization to inform the agent about available features and methods. See protocol docs: Client Capabilities Type: Object Properties:

​

ClientNesCapabilities

NES capabilities advertised by the client during initialization. Type: Object Properties:

​

ConfigOptionUpdate

Session configuration options have been updated. Type: Object Properties:

​

Content

Standard content block (text, images, resources). Type: Object Properties:

​

ContentBlock

Content blocks represent displayable information in the Agent Client Protocol. They provide a structured way to handle various types of user-facing content—whether it’s text from language models, images for analysis, or embedded resources for context. Content blocks appear in:

• User prompts sent via session/prompt
• Language model output streamed through session/update notifications
• Progress updates and results from tool calls

This structure is compatible with the Model Context Protocol (MCP), enabling agents to seamlessly forward content from MCP tool outputs without transformation. See protocol docs: Content Type: Union

​

ContentChunk

A streamed item of content Type: Object Properties:

​

Cost

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Cost information for a session. Type: Object Properties:

​

CurrentModeUpdate

The current mode of the session has changed See protocol docs: Session Modes Type: Object Properties:

​

Diff

A diff representing file modifications. Shows changes to files in a format suitable for display in the client UI. See protocol docs: Content Type: Object Properties:

​

ElicitationAcceptAction

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. The user accepted the elicitation and provided content. Type: Object Properties:

​

ElicitationCapabilities

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Elicitation capabilities supported by the client. Type: Object Properties:

​

ElicitationContentValue

Type: Union

​

ElicitationFormCapabilities

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Form-based elicitation capabilities. Type: Object Properties:

​

ElicitationFormMode

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Form-based elicitation mode where the client renders a form from the provided schema. Type: Union Shared properties: Variants:

​

ElicitationId

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Unique identifier for an elicitation. Type: string

​

ElicitationPropertySchema

Property schema for elicitation form fields. Each variant corresponds to a JSON Schema "type" value. Single-select enums use the String variant with enum or oneOf set. Multi-select enums use the Array variant. Type: Union

​

ElicitationRequestScope

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Request-scoped elicitation, tied to a specific JSON-RPC request outside of a session (e.g., during auth/configuration phases before any session is started). Type: Object Properties:

​

ElicitationSchema

Type-safe elicitation schema for requesting structured user input. This represents a JSON Schema object with primitive-typed properties, as required by the elicitation specification. Type: Object Properties:

​

ElicitationSchemaType

Type discriminator for elicitation schemas. Type: Union

​

ElicitationSessionScope

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Session-scoped elicitation, optionally tied to a specific tool call. When tool_call_id is set, the elicitation is tied to a specific tool call. This is useful when an agent receives an elicitation from an MCP server during a tool call and needs to redirect it to the user. Type: Object Properties:

​

ElicitationStringType

Items definition for untitled multi-select enum properties. Type: Union

​

ElicitationUrlCapabilities

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. URL-based elicitation capabilities. Type: Object Properties:

​

ElicitationUrlMode

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. URL-based elicitation mode where the client directs the user to a URL. Type: Union Shared properties: Variants:

​

EmbeddedResource

The contents of a resource, embedded into a prompt or tool call result. Type: Object Properties:

​

EmbeddedResourceResource

Resource content that can be embedded in a message. Type: Union

​

EnumOption

A titled enum option with a const value and human-readable title. Type: Object Properties:

​

EnvVariable

An environment variable to set when launching an MCP server. Type: Object Properties:

​

Error

JSON-RPC error object. Represents an error that occurred during method execution, following the JSON-RPC 2.0 error object specification with optional additional data. See protocol docs: JSON-RPC Error Object Type: Object Properties:

​

ErrorCode

Predefined error codes for common JSON-RPC and ACP-specific errors. These codes follow the JSON-RPC 2.0 specification for standard errors and use the reserved range (-32000 to -32099) for protocol-specific errors. Type: Union

​

ExtNotification

Allows the Agent to send an arbitrary notification that is not part of the ACP spec. Extension notifications provide a way to send one-way messages for custom functionality while maintaining protocol compatibility. See protocol docs: Extensibility

​

ExtRequest

Allows for sending an arbitrary request that is not part of the ACP spec. Extension methods provide a way to add custom functionality while maintaining protocol compatibility. See protocol docs: Extensibility

​

ExtResponse

Allows for sending an arbitrary response to an ExtRequest that is not part of the ACP spec. Extension methods provide a way to add custom functionality while maintaining protocol compatibility. See protocol docs: Extensibility

​

FileSystemCapabilities

File system capabilities that a client may support. See protocol docs: FileSystem Type: Object Properties:

​

HttpHeader

An HTTP header to set when making requests to the MCP server. Type: Object Properties:

​

ImageContent

An image provided to or from an LLM. Type: Object Properties:

​

Implementation

Metadata about the implementation of the client or agent. Describes the name and version of an MCP implementation, with an optional title for UI representation. Type: Object Properties:

​

IntegerPropertySchema

Schema for integer properties in an elicitation form. Type: Object Properties:

​

LlmProtocol

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Well-known API protocol identifiers for LLM providers. Agents and clients MUST handle unknown protocol identifiers gracefully. Protocol names beginning with _ are free for custom use, like other ACP extension methods. Protocol names that do not begin with _ are reserved for the ACP spec. Type: Union

​

LogoutCapabilities

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Logout capabilities supported by the agent. By supplying \{\} it means that the agent supports the logout method. Type: Object Properties:

​

McpCapabilities

MCP capabilities supported by the agent Type: Object Properties:

​

McpServer

Configuration for connecting to an MCP (Model Context Protocol) server. MCP servers provide tools and context that the agent can use when processing prompts. See protocol docs: MCP Servers Type: Union

​

McpServerHttp

HTTP transport configuration for MCP. Type: Object Properties:

​

McpServerSse

SSE transport configuration for MCP. Type: Object Properties:

​

McpServerStdio

Stdio transport configuration for MCP. Type: Object Properties:

​

ModelId

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. A unique identifier for a model. Type: string

​

ModelInfo

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Information about a selectable model. Type: Object Properties:

​

MultiSelectItems

Items for a multi-select (array) property schema. Type: Union

​

MultiSelectPropertySchema

Schema for multi-select (array) properties in an elicitation form. Type: Object Properties:

​

NesCapabilities

NES capabilities advertised by the agent during initialization. Type: Object Properties:

​

NesContextCapabilities

Context capabilities the agent wants attached to each suggestion request. Type: Object Properties:

​

NesDiagnostic

A diagnostic (error, warning, etc.). Type: Object Properties:

​

NesDiagnosticSeverity

Severity of a diagnostic. Type: Union

​

NesDiagnosticsCapabilities

Capabilities for diagnostics context. Type: Object Properties:

​

NesDocumentDidChangeCapabilities

Capabilities for document/didChange events. Type: Object Properties:

​

NesDocumentDidCloseCapabilities

Marker for document/didClose capability support. Type: Object Properties:

​

NesDocumentDidFocusCapabilities

Marker for document/didFocus capability support. Type: Object Properties:

​

NesDocumentDidOpenCapabilities

Marker for document/didOpen capability support. Type: Object Properties:

​

NesDocumentDidSaveCapabilities

Marker for document/didSave capability support. Type: Object Properties:

​

NesDocumentEventCapabilities

Document event capabilities the agent wants to receive. Type: Object Properties:

​

NesEditHistoryCapabilities

Capabilities for edit history context. Type: Object Properties:

​

NesEditHistoryEntry

An entry in the edit history. Type: Object Properties:

​

NesEditSuggestion

A text edit suggestion. Type: Object Properties:

​

NesEventCapabilities

Event capabilities the agent can consume. Type: Object Properties:

​

NesExcerpt

A code excerpt from a file. Type: Object Properties:

​

NesJumpCapabilities

Marker for jump suggestion support. Type: Object Properties:

​

NesJumpSuggestion

A jump-to-location suggestion. Type: Object Properties:

​

NesOpenFile

An open file in the editor. Type: Object Properties:

​

NesOpenFilesCapabilities

Capabilities for open files context. Type: Object Properties:

​

NesRecentFile

A recently accessed file. Type: Object Properties:

​

NesRecentFilesCapabilities

Capabilities for recent files context. Type: Object Properties:

​

NesRejectReason

The reason a suggestion was rejected. Type: Union

​

NesRelatedSnippet

A related code snippet from a file. Type: Object Properties:

​

NesRelatedSnippetsCapabilities

Capabilities for related snippets context. Type: Object Properties:

​

NesRenameCapabilities

Marker for rename suggestion support. Type: Object Properties:

​

NesRenameSuggestion

A rename symbol suggestion. Type: Object Properties:

​

NesRepository

Repository metadata for an NES session. Type: Object Properties:

​

NesSearchAndReplaceCapabilities

Marker for search and replace suggestion support. Type: Object Properties:

​

NesSearchAndReplaceSuggestion

A search-and-replace suggestion. Type: Object Properties:

​

NesSuggestContext

Context attached to a suggestion request. Type: Object Properties:

​

NesSuggestion

A suggestion returned by the agent. Type: Union

​

NesTextEdit

A text edit within a suggestion. Type: Object Properties:

​

NesTriggerKind

What triggered the suggestion request. Type: Union

​

NesUserAction

A user action (typing, cursor movement, etc.). Type: Object Properties:

​

NesUserActionsCapabilities

Capabilities for user actions context. Type: Object Properties:

​

NumberPropertySchema

Schema for number (floating-point) properties in an elicitation form. Type: Object Properties:

​

PermissionOption

An option presented to the user when requesting permission. Type: Object Properties:

​

PermissionOptionId

Unique identifier for a permission option. Type: string

​

PermissionOptionKind

The type of permission option being presented to the user. Helps clients choose appropriate icons and UI treatment. Type: Union

​

Plan

An execution plan for accomplishing complex tasks. Plans consist of multiple entries representing individual tasks or goals. Agents report plans to clients to provide visibility into their execution strategy. Plans can evolve during execution as the agent discovers new requirements or completes tasks. See protocol docs: Agent Plan Type: Object Properties:

​

PlanEntry

A single entry in the execution plan. Represents a task or goal that the assistant intends to accomplish as part of fulfilling the user’s request. See protocol docs: Plan Entries Type: Object Properties:

​

PlanEntryPriority

Priority levels for plan entries. Used to indicate the relative importance or urgency of different tasks in the execution plan. See protocol docs: Plan Entries Type: Union

​

PlanEntryStatus

Status of a plan entry in the execution flow. Tracks the lifecycle of each task from planning through completion. See protocol docs: Plan Entries Type: Union

​

Position

A zero-based position in a text document. The meaning of character depends on the negotiated position encoding. Type: Object Properties:

​

PositionEncodingKind

The encoding used for character offsets in positions. Follows the same conventions as LSP 3.17. The default is UTF-16. Type: Union

​

PromptCapabilities

Prompt capabilities supported by the agent in session/prompt requests. Baseline agent functionality requires support for ContentBlock::Text and ContentBlock::ResourceLink in prompt requests. Other variants must be explicitly opted in to. Capabilities for different types of content in prompt requests. Indicates which content types beyond the baseline (text and resource links) the agent can process. See protocol docs: Prompt Capabilities Type: Object Properties:

​

ProtocolVersion

Protocol version identifier. This version is only bumped for breaking changes. Non-breaking changes should be introduced via capabilities. Type: integer (uint16)

​

ProviderCurrentConfig

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Current effective non-secret routing configuration for a provider. Type: Object Properties:

​

ProviderInfo

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Information about a configurable LLM provider. Type: Object Properties:

​

ProvidersCapabilities

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Provider configuration capabilities supported by the agent. By supplying \{\} it means that the agent supports provider configuration methods. Type: Object Properties:

​

Range

A range in a text document, expressed as start and end positions. Type: Object Properties:

​

RequestId

JSON RPC Request Id An identifier established by the Client that MUST contain a String, Number, or NULL value if included. If it is not included it is assumed to be a notification. The value SHOULD normally not be Null [1] and Numbers SHOULD NOT contain fractional parts [2] The Server MUST reply with the same value in the Response object if included. This member is used to correlate the context between the two objects. [1] The use of Null as a value for the id member in a Request object is discouraged, because this specification uses a value of Null for Responses with an unknown id. Also, because JSON-RPC 1.0 uses an id value of Null for Notifications this could cause confusion in handling. [2] Fractional parts may be problematic, since many decimal fractions cannot be represented exactly as binary fractions. Type: Union

​

RequestPermissionOutcome

The outcome of a permission request. Type: Union

​

ResourceLink

A resource that the server is capable of reading, included in a prompt or tool call result. Type: Object Properties:

​

Role

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

​

SelectedPermissionOutcome

The user selected one of the provided options. Type: Object Properties:

​

SessionAdditionalDirectoriesCapabilities

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Capabilities for additional session directories support. By supplying \{\} it means that the agent supports the additionalDirectories field on supported session lifecycle requests and session/list. Type: Object Properties:

​

SessionCapabilities

Session capabilities supported by the agent. As a baseline, all Agents MUST support session/new, session/prompt, session/cancel, and session/update. Optionally, they MAY support other session methods and notifications by specifying additional capabilities. Note: session/load is still handled by the top-level load_session capability. This will be unified in future versions of the protocol. See protocol docs: Session Capabilities Type: Object Properties:

​

SessionCloseCapabilities

Capabilities for the session/close method. By supplying \{\} it means that the agent supports closing of sessions. Type: Object Properties:

​

SessionConfigBoolean

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. A boolean on/off toggle session configuration option payload. Type: Object Properties:

​

SessionConfigGroupId

Unique identifier for a session configuration option value group. Type: string

​

SessionConfigId

Unique identifier for a session configuration option. Type: string

​

SessionConfigOption

A session configuration option selector and its current state. Type: Union Shared properties: Variants:

​

SessionConfigOptionCategory

Semantic category for a session configuration option. This is intended to help Clients distinguish broadly common selectors (e.g. model selector vs session mode selector vs thought/reasoning level) for UX purposes (keyboard shortcuts, icons, placement). It MUST NOT be required for correctness. Clients MUST handle missing or unknown categories gracefully. Category names beginning with _ are free for custom use, like other ACP extension methods. Category names that do not begin with _ are reserved for the ACP spec. Type: Union

​

SessionConfigSelect

A single-value selector (dropdown) session configuration option payload. Type: Object Properties:

​

SessionConfigSelectGroup

A group of possible values for a session configuration option. Type: Object Properties:

​

SessionConfigSelectOption

A possible value for a session configuration option. Type: Object Properties:

​

SessionConfigSelectOptions

Possible values for a session configuration option. Type: Union

​

SessionConfigValueId

Unique identifier for a session configuration option value. Type: string

​

SessionForkCapabilities

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Capabilities for the session/fork method. By supplying \{\} it means that the agent supports forking of sessions. Type: Object Properties:

​

SessionId

A unique identifier for a conversation session between a client and agent. Sessions maintain their own context, conversation history, and state, allowing multiple independent interactions with the same agent. See protocol docs: Session ID Type: string

​

SessionInfo

Information about a session returned by session/list Type: Object Properties:

​

SessionInfoUpdate

Update to session metadata. All fields are optional to support partial updates. Agents send this notification to update session information like title or custom metadata. This allows clients to display dynamic session names and track session state changes. Type: Object Properties:

​

SessionListCapabilities

Capabilities for the session/list method. By supplying \{\} it means that the agent supports listing of sessions. Type: Object Properties:

​

SessionMode

A mode the agent can operate in. See protocol docs: Session Modes Type: Object Properties:

​

SessionModeId

Unique identifier for a Session Mode. Type: string

​

SessionModeState

The set of modes and the one currently active. Type: Object Properties:

​

SessionModelState

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. The set of models and the one currently active. Type: Object Properties:

​

SessionResumeCapabilities

Capabilities for the session/resume method. By supplying \{\} it means that the agent supports resuming of sessions. Type: Object Properties:

​

SessionUpdate

Different types of updates that can be sent during session processing. These updates provide real-time feedback about the agent’s progress. See protocol docs: Agent Reports Output Type: Union

​

StopReason

Reasons why an agent stops processing a prompt turn. See protocol docs: Stop Reasons Type: Union

​

StringFormat

String format types for string properties in elicitation schemas. Type: Union

​

StringPropertySchema

Schema for string properties in an elicitation form. When enum or oneOf is set, this represents a single-select enum with "type": "string". Type: Object Properties:

​

Terminal

Embed a terminal created with terminal/create by its id. The terminal must be added before calling terminal/release. See protocol docs: Terminal Type: Object Properties:

​

TerminalExitStatus

Exit status of a terminal command. Type: Object Properties:

​

TextContent

Text provided to or from an LLM. Type: Object Properties:

​

TextDocumentContentChangeEvent

A content change event for a document. When range is None, text is the full content of the document. When range is Some, text replaces the given range. Type: Object Properties:

​

TextDocumentSyncKind

How the agent wants document changes delivered. Type: Union

​

TextResourceContents

Text-based resource contents. Type: Object Properties:

​

TitledMultiSelectItems

Items definition for titled multi-select enum properties. Type: Object Properties:

​

ToolCall

Represents a tool call that the language model has requested. Tool calls are actions that the agent executes on behalf of the language model, such as reading files, executing code, or fetching data from external sources. See protocol docs: Tool Calls Type: Object Properties:

​

ToolCallContent

Content produced by a tool call. Tool calls can produce different types of content including standard content blocks (text, images) or file diffs. See protocol docs: Content Type: Union

​

ToolCallId

Unique identifier for a tool call within a session. Type: string

​

ToolCallLocation

A file location being accessed or modified by a tool. Enables clients to implement “follow-along” features that track which files the agent is working with in real-time. See protocol docs: Following the Agent Type: Object Properties:

​

ToolCallStatus

Execution status of a tool call. Tool calls progress through different statuses during their lifecycle. See protocol docs: Status Type: Union

​

ToolCallUpdate

An update to an existing tool call. Used to report progress and results as tools execute. All fields except the tool call ID are optional - only changed fields need to be included. See protocol docs: Updating Type: Object Properties:

​

ToolKind

Categories of tools that can be invoked. Tool kinds help clients choose appropriate icons and optimize how they display tool execution progress. See protocol docs: Creating Type: Union

​

UnstructuredCommandInput

All text that was typed after the command name is provided as input. Type: Object Properties:

​

UntitledMultiSelectItems

Items definition for untitled multi-select enum properties. Type: Object Properties:

​

Usage

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Token usage information for a prompt turn. Type: Object Properties:

​

UsageUpdate

UNSTABLE This capability is not part of the spec yet, and may be removed or changed at any point. Context window and cost update for a session. Type: Object Properties:

​

WorkspaceFolder

A workspace folder. Type: Object Properties: