McpTool

Turns an MCP Tool into an ADK BaseTool.

The tool holds no session of its own: it fetches the shared session from mcpSessionManager on each call and, on failure, asks the manager to reinitialize it. Because the manager owns the session pool, a reinit is seen by every tool sharing the session and the toolset can close them all via SessionManager.close.

Types

Link copied to clipboard
object Companion

Properties

Link copied to clipboard

The custom metadata of the tool.

Link copied to clipboard

The description of the tool.

Link copied to clipboard

Whether the tool's final result will be delivered out-of-band. When true, the framework marks the call as long-running and uses the tool's return value as the function-response payload. Returning Unit means "no response yet": the FR event is suppressed so the function-call event (which carries the call id in longRunningToolIds and is thus the turn's final response) ends the turn without re-invoking the model. A non-Unit return -- including an explicit empty Map -- is treated as a real response and emitted. (Unit suppression aligns with Python; Java instead always emits {}.) The longRunningToolIds id also drives the resumable-mode pause gate so the invocation can be resumed later via a user-injected function-response.

Link copied to clipboard

The name of the tool.

Functions

Link copied to clipboard
open override fun close()
Link copied to clipboard
open override fun declaration(): FunctionDeclaration?

Returns the underlying function declaration.

Link copied to clipboard
open suspend fun processLlmRequest(toolContext: ToolContext, llmRequest: LlmRequest): LlmRequest

Processes the LLM request before it is sent.

Link copied to clipboard
open suspend override fun run(context: ToolContext, args: Map<String, Any?>): Any

Executes the tool and returns its result.