You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Streamable HTTP transport fails when accessing MCP server on Cloud Run using sdk #1053
When using the python-sdk with transport set to streamable-http, the connection to a remote MCP server deployed on Google Cloud Run does not establish. The API stays in a pending state, and no updates are received.
However, the same MCP server works fine under the following conditions:
When accessed via Google Cloud Proxy
When transport is changed to SSE
When using the JS SDK, streamable-http transport works without issues
This suggests a compatibility or configuration issue specifically between python-sdk's streamable-http transport and direct access to Cloud Run URLs.
Any update on possible workarounds tried? Still fail to connect trying to wrap FastMCP using fastAPI, when deployed locally, connection has no issues. @sidgangs99
Thanks for the report. The v2 rework changed the code this targets, so it no longer applies as-is. Closing this as part of a wider backlog cleanup following the v2 launch. If it's still relevant, feel free to reopen.
Activity
eiseleMichael commentedon Jun 30, 2025
A quick workaround would be to use FastAPI to wrap your FastMCP server, this is how we are running them currently in Cloud Run.
and use uvicorn (or any other server) to run it.
In your docker file:
santosarns commentedon Jul 15, 2025
Any update on possible workarounds tried? Still fail to connect trying to wrap FastMCP using fastAPI, when deployed locally, connection has no issues. @sidgangs99
Have you tried this out? @eiseleMichael
sachin-philip commentedon Aug 9, 2025
@santosarns , @sidgangs99 did you manage to solve this without FastAPI wrapper?
adefemi171 commentedon Jan 10, 2026
Also facing same issue
maxisbey commentedon Aug 10, 2026
Thanks for the report. The v2 rework changed the code this targets, so it no longer applies as-is. Closing this as part of a wider backlog cleanup following the v2 launch. If it's still relevant, feel free to reopen.
AI Disclaimer