[v2] Expose request cancellation on MCPServer tool Context

What happened?

With mcp==2.1.0, a tool registered through the high-level mcp.server.mcpserver.MCPServer API receives mcp.server.mcpserver.Context. That context does not expose a public cancel_requested event, although the lower-level mcp.shared.context.BaseContext does.

from mcp.server.mcpserver.context import Context as MCPServerContext
from mcp.shared.context import BaseContext

assert not hasattr(MCPServerContext, "cancel_requested")
assert hasattr(BaseContext, "cancel_requested")

The server dispatcher processes notifications/cancelled and holds the event in its per-request dispatch context, but normal tool handlers cannot cooperatively observe it through the supported high-level context API. A handler that owns cleanup-sensitive work (for example, a bounded child process) must either rely only on task interruption or traverse private session/dispatch internals to relay cancellation.

Expected behavior

Expose the current request's cancellation event on the high-level tool context (for example, await ctx.cancel_requested.wait()), or document an equivalent supported API. It should allow a handler to trigger its own cooperative cleanup without using private SDK attributes.

If this is already addressed in a later release, a version pointer would also resolve the report; the reproduction above is against 2.1.0.

Reproduction steps

1. Install mcp==2.1.0.
2. Register an async tool with MCPServer that accepts its injected Context.
3. Attempt to access ctx.cancel_requested; the attribute is absent.
4. Compare with BaseContext.cancel_requested, which is present.

SDK version

mcp==2.1.0 (Python 3.12)

Area

Server / high-level MCPServer tool context API.

AI assistance disclosure: drafted with AI assistance; the reporter is responsible for this report.

Comece em mcp.server.mcpserver.MCPServer e em seu mcp.server.mcpserver.context.Context injetado; em seguida, compare como mcp.shared.context.BaseContext expõe cancel_requested e como notifications/cancelled é armazenado no contexto de dispatch por solicitação. A tarefa estará concluída quando os handlers de ferramentas de alto nível puderem usar um evento de cancelamento compatível sem acessar os detalhes internos privados da sessão ou do dispatch, com cobertura para a reprodução relatada.