Repository navigation
sse_app() ignores mount prefix, resulting in 404 from client #412
Description
Activity
This might be related with #386
This might be related with #386
The clients shouldn't be patching the endpoints. The server should just give it the right endpoint during the handshake.
Reacted by Chinseok Leeis there any workaround?
application = Starlette(
routes=[
Mount("/", app=mcp.sse_app()), # HERE !!!
]
)can't get the routes either?
what's the standard way of linking a fastapi/starlette app with mcp? i need some custom routes
This is all going to change once streamable HTTP lands, but my work-around for now is to just update
/etc/hosts(MacOS/Linux) or Hosts File Editor (Windows) to add two hostnamesbackendandmcp. Then just serve MCP/SSE on only themcphostname.Something like:
# entrypoint.py from starlette.applications import Starlette from starlette.routing import Mount, Host from django.core.asgi import get_asgi_application django_http_app = get_asgi_application() from backend.server import mcp_app routes = [] application = Starlette(routes=routes) application.router.routes.append(Host('backend', app=django_http_app)) application.router.routes.append(Host('mcp', app=mcp_app.sse_app()))There is in issue currently with message routing for non-root mounts. It seems to be ignored by
sse_app. Here is a workaround.As FastAPI is a subclass of Starlette, this works just as well for FastAPI. This is just a slight modification of the sse_app method
def register_mcp_router( starlette_app: Starlette, mcp_server: FastMCP, base_path: str, ): sse = SseServerTransport(f"{base_path}/messages/") async def handle_sse(request: Request) -> None: async with sse.connect_sse( request.scope, request.receive, request._send, # noqa: SLF001 ) as (read_stream, write_stream): await mcp_server._mcp_server.run( read_stream, write_stream, mcp_server._mcp_server.create_initialization_options(), ) starlette_app.add_route(f"{base_path}/sse", handle_sse) starlette_app.mount(f"{base_path}/messages/", sse.handle_post_message)
Other issues/PRs raising the same bug
Reacted by Lee Pak ShuangReacted by V, George Burton and Dheeraj OrugantyI ran into this also and am trying the above. A complete example would be really helpful.
In my example the MCP server is written within an openfaas function mounted at
http://127.0.0.1:8080/function/mcp- then/sseand/messagesare sub-paths. The path of/function/mcpis stripped by the openfaas gateway before the request hits the HTTP server.I still seem to get the same errors from the client with the above workaround
from fastmcp import Client from fastmcp.client.transports import ( SSETransport ) import os from dotenv import load_dotenv import asyncio import httpx load_dotenv() API_KEY = os.getenv('API_KEY') async def main(): base_url = "http://127.0.0.1:8080/function/mcp/sse" # Connect to a server over SSE (common for web-based MCP servers) transport = SSETransport( f"{base_url}" ) async with Client(transport) as client: await client.ping() print(await client.call_tool("list_functions")) asyncio.run(main())
Error in post_writer: Client error '404 Not Found' for url 'http://127.0.0.1:8080/messages/?session_id=7054b5ed39574cb28470f6308868c6a8' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404In other words, the server needs to be mounted at
/to work... since all paths are stripped off before/function/mcp- but it also needs to reply back as if it were mounted at/function/mcpsince the client is unable to understand relative paths.Have a potential fix. #524
I’m experiencing a very similar issue, but in my case, the URL prefix is not defined inside the application code using Mount. Instead, my MCP service is deployed behind an external reverse proxy that uses a multi-level path to distinguish between services.
For example, my SSE server is mounted at /sse, but it's exposed publicly at:
https://****-mcp-server/my/sseIn this case, /my is part of a multi-level URL path added by the reverse proxy, which forwards requests to the root of my MCP server.
When I configure the MCP client to use this kind of multi-level path, I encounter a 404 error.
Reacted by Lize Cai#540 is the latest on this
Reacted by tim-watcha and Lize CaiI just hit the same problem. Could you please consider allowing for the
base_pathto be supplied?
Example modification inpython-sdk/src/mcp/server/fastmcp/server.py:def sse_app(self, base_path: str = '') -> Starlette: """Return an instance of the SSE server app.""" sse = SseServerTransport(f'{base_path}{self.settings.message_path}')
The original code looks like this:
def sse_app(self) -> Starlette: """Return an instance of the SSE server app.""" sse = SseServerTransport(self.settings.message_path) async def handle_sse(request: Request) -> None: async with sse.connect_sse( request.scope, request.receive, request._send, # type: ignore[reportPrivateUsage] ) as streams: await self._mcp_server.run( streams[0], streams[1], self._mcp_server.create_initialization_options(), ) return Starlette( debug=self.settings.debug, routes=[ Route(self.settings.sse_path, endpoint=handle_sse), Mount(self.settings.message_path, app=sse.handle_post_message), ], )
Exposing the
base_pathas suggested would allow for mounting withStarletteas follows:Mount('/mcp', mcp.sse_app(base_path='/mcp')),
It is a bit redundant, but it works.
Reacted by Diego QuirozI’m experiencing a very similar issue, but in my case, the URL prefix is not defined inside the application code using Mount. Instead, my MCP service is deployed behind an external reverse proxy that uses a multi-level path to distinguish between services.
For example, my SSE server is mounted at /sse, but it's exposed publicly at: https://****-mcp-server/my/sse
In this case, /my is part of a multi-level URL path added by the reverse proxy, which forwards requests to the root of my MCP server.
When I configure the MCP client to use this kind of multi-level path, I encounter a 404 error.
I have the same issue, and I think this should be resolved in client side. Open a feature request for it: #795
It's still not clear what is supposed to happen from the docs
app = Starlette( routes=[ Mount('/search', app=mcp.sse_app()), ] )
When I do this
http://localhost:8000/search/sseseems to work buthttp://localhost:8000/searchgives 404Is that intended?
Describe the bug
When mounting sse_app() from FastMCP with a URL prefix using Starlette’s Mount, the SSE stream still returns the default /messages/ endpoint without the prefix. This causes the MCP client to resolve an incorrect URL (e.g., /messages/ instead of /mcp/messages/), resulting in a 404 error.
To Reproduce
Steps to reproduce the behavior:
At this point, the MCP client performs a
urljoinoperation between the SSE URL (http://127.0.0.1:8000/mcp/sse) and the endpoint path (/messages/). This causes the resolved endpoint URL to become http://127.0.0.1:8000/messages/.Expected behavior
The SSE stream should return the correct full path reflecting the prefix, e.g.:
This would allow the client to connect to the actual valid message endpoint.
Screenshots
If applicable, add screenshots to help explain your problem.
Desktop (please complete the following information):
Smartphone (please complete the following information):
Additional context
This behavior seems to originate from hardcoded endpoint generation inside sse_app():
python-sdk/src/mcp/server/sse.py
Line 98 in c2ca8e0
It would be great to have support for specifying a prefix in sse_app() or for the prefix to be auto-detected from the ASGI scope.
Thank you!