modelcontextprotocol / modelcontextprotocol/python-sdk
In-process callback failures break tool calls and notification sends
Nadie ha tomado este issue todavía.
- Lenguaje dominante
- Python
- Estrellas
- 24.3k
- Forks
- 4k
- Merge medio
- 1 d 1 h
- PR fusionados (30 d)
- 31
Descripción
Initial Checks
- I confirm that I am using the newest release of the 2.x line.
- I confirm that I searched the issue tracker before opening this issue.
Release line
2.x (current stable)
Description
Client(server) uses DirectDispatcher. If a progress callback raises, that exception crosses back into server tool execution, so a tool that otherwise returns successfully fails with UnexpectedToolError. DirectDispatcher also lets an inbound notification handler exception escape back to the sender's notify() call.
The stream-backed JSONRPCDispatcher logs and contains both callback failures. I expected the in-process path to keep the same boundary: log the callback failure, but let the protocol operation continue.
I have a small patch and regression tests for both paths and would like to fix this if maintainers want an outside pull request.
I used GitHub Copilot CLI to inspect the dispatcher paths, write the patch, and draft this report. I verified the reproduction and tests.
Example Code
import anyio
from mcp import Client
from mcp.server.mcpserver import Context, MCPServer
server = MCPServer("callback-repro")
@server.tool()
async def work(context: Context) -> str:
await context.report_progress(1, 1)
return "done"
async def broken_progress(progress: float, total: float | None, message: str | None) -> None:
raise RuntimeError("consumer failed")
async def main() -> None:
async with Client(server, mode="2026-07-28") as client:
result = await client.call_tool("work", progress_callback=broken_progress)
print(result.content[0].text)
anyio.run(main)
Current main ends with:
UnexpectedToolError: Error executing tool work
The tool should print done. The callback failure should still be logged.
Verification
With only the regression tests applied to clean main:
uv run --frozen pytest tests/shared/test_dispatcher.py \
-k 'progress_callback_exception_does_not_fail_request or notification_handler_exception_does_not_reach_sender' -q
# 2 failed, 2 passed. Both DirectDispatcher cases failed.
With the two callback guards applied:
uv run --frozen pytest tests/shared/test_dispatcher.py \
-k 'progress_callback_exception_does_not_fail_request or notification_handler_exception_does_not_reach_sender' -q
# 4 passed
Python & MCP Python SDK
Python 3.12.13
mcp 2.1.1
mcp 2.1.2.dev4+d060b36e at d060b36e1d095ef6e93e07ba5d59bb69b2ad449a
macOS
Guía de contribución
Primeros pasos
- Lee el issue completo y luego la guía de contribución del proyecto.
- Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
- Haz un fork del repositorio y trabaja en una rama.
- Abre un pull request que haga referencia al número del issue.
Línea de trabajo
Comienza en las rutas de DirectDispatcher y compara su gestión de fallos de callbacks con la de JSONRPCDispatcher respaldado por streams. Ejecuta tests/shared/test_dispatcher.py con los dos casos -k indicados para reproducir los fallos. Se considera terminado cuando ambos casos de DirectDispatcher pasan, las llamadas exitosas a herramientas y los envíos de notificaciones siguen funcionando, y los fallos de callbacks se registran.
Escrito por el modelo de indexación a partir del texto del issue.
Evaluación
- Stack tecnológico
- python
- Área
- backend-api-design
- Tipo de issue
- Error
- Dificultad
- 3/5
- Tiempo estimado
- 1-2 días
- Estado de actividad
- Activo
- Claridad
- Bien especificado
- Aptitud para principiantes
- 84/100