modelcontextprotocol / modelcontextprotocol/python-sdk
Duplicate `initialize` with changed parameters can overwrite `ServerSession.client_params`
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 24.3k
- Forks
- 4k
- Avg merge
- 1d 1h
- Merged PRs (30d)
- 31
Description
Initial Checks
- I confirm that I'm using the latest version of MCP Python SDK
- I confirm that I searched for my issue in https://github.com/modelcontextprotocol/python-sdk/issues before opening this issue
Description
After a normal MCP initialization flow, a Python SDK server accepts another initialize request on the same live connection/session and returns a normal initialize result.
I agree that the spec does not explicitly say every repeated initialize must be rejected. My concern is narrower: after the session has already moved into normal operation, a later same-session initialize with different parameters can update the server's stored client initialization parameters.
The MCP lifecycle documentation describes initialization as the first client/server interaction and says the operation phase uses the negotiated protocol version and capabilities. In that model, silently changing the stored client identity/capabilities/protocol version after operation has begun seems surprising unless the SDK intentionally supports same-session renegotiation.
src/mcp/server/session.pystores the client initialization request inServerSession._client_params.ServerSession.client_paramsexposes that value.- In both the stable release and the
mainsnapshot I tested, theInitializeRequesthandler assignsself._client_params = params. ServerSession.check_client_capability()later readsself._client_params.capabilities, so a duplicateinitializewith differentcapabilitiescan affect capability-gated server logic.
What I observed
Reproduced on stable v1.27.1 (77431ebe7dda9ed0c61451b22d3e7f8d981bc092):
stdio: a secondinitializewas accepted afternotifications/initialized; a laterpingstill succeeded.- stateful Streamable HTTP: a second
initializewas accepted afternotifications/initialized; a laterpingstill succeeded. - stateless Streamable HTTP: a second
initializewas accepted afternotifications/initialized; a laterpingstill succeeded.
For stateful Streamable HTTP on v1.27.1, I added a local diagnostic tool that reads ctx.session.client_params before and after the duplicate initialize on the same session:
Duplicate initialize parameters |
Observed result |
|---|---|
| Same parameters | No state change |
Changed clientInfo and capabilities |
client_params.clientInfo and client_params.capabilities changed |
Older protocolVersion (2024-11-05) |
client_params.protocolVersion and client_params.clientInfo changed |
On the frozen main snapshot (161834d4aee2633c42d3976c8f8751b6c4d947d5), the same duplicate-initialize acceptance still reproduced. My diagnostic snapshot directly observed client_params.capabilities changing after a duplicate initialize with changed capabilities on both stdio and stateful Streamable HTTP.
Expected behavior
If same-session duplicate initialization is not intended, I would expect the server to reject the later initialize after normal operation has begun, for example with a JSON-RPC -32600 Invalid Request error.
If this tolerant behavior is intentional, I think it should be either:
- a no-op once the session has already initialized, especially for changed parameters, or
- documented as same-session renegotiation, including whether
ServerSession.client_params, client capabilities, client identity, and protocol version are allowed to change.
Example Code
import json
try:
# Current main branch naming.
from mcp.server.mcpserver import Context, MCPServer
except ImportError:
# Latest stable release naming.
from mcp.server.fastmcp import Context, FastMCP as MCPServer
mcp = MCPServer("dup-init-repro")
def field(obj, *names):
if obj is None:
return None
for name in names:
if hasattr(obj, name):
return getattr(obj, name)
return None
def dump(value):
if value is None:
return None
if hasattr(value, "model_dump"):
return value.model_dump(mode="json", by_alias=True)
return value
@mcp.tool()
async def session_snapshot(ctx: Context) -> str:
params = ctx.session.client_params
return json.dumps(
{
"protocolVersion": field(params, "protocolVersion", "protocol_version"),
"clientInfo": dump(field(params, "clientInfo", "client_info")),
"clientCapabilities": dump(field(params, "capabilities")),
},
separators=(",", ":"),
default=str,
)
if __name__ == "__main__":
mcp.run(transport="streamable-http")
'''
Request sequence:
1. Start the server.
2. Send a normal `initialize`.
3. Send `notifications/initialized`.
4. Call the `session_snapshot` tool and record the returned JSON.
5. Send another `initialize` on the same live session, but change `clientInfo` and/or `capabilities`.
6. Call `session_snapshot` again on the same session.
On `v1.27.1`, the second snapshot reflects the changed `clientInfo` / `capabilities`. On the `main` snapshot I tested, the second snapshot still reflects changed `capabilities`.
'''
Python & MCP Python SDK
- Python: `3.12.3`
- MCP Python SDK: `mcp==1.27.1` (`v1.27.1`, `77431ebe7dda9ed0c61451b22d3e7f8d981bc092`)
- Also reproduced on `main` snapshot `161834d4aee2633c42d3976c8f8751b6c4d947d5` (`v1.25.0-159-g161834d4`, pinned 2026-05-11)
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with src/mcp/server/session.py, especially the InitializeRequest handler and ServerSession.client_params. Reproduce the duplicate-initialize sequence described in the issue across stdio and stateful or stateless Streamable HTTP, then inspect how client parameters are read afterward. Done means the chosen duplicate-initialization behavior is consistent and no unintended client parameters are overwritten.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- api, backend
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100