Pin mcp SDK to patched fork for stateless task leak fix#631
Draft
Pin mcp SDK to patched fork for stateless task leak fix#631
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Why
The upstream MCP Python SDK has a memory leak where stateless HTTP request tasks accumulate in the global task group when clients disconnect mid-request (modelcontextprotocol/python-sdk#1764). This causes unbounded memory growth in long-running MCP servers like our remote dbt MCP proxy.
The fix (request-scoped task groups) also introduces a regression where SSE streams don't close cleanly on shutdown — reverse proxies see connection resets instead of clean HTTP close. A graceful drain step resolves this.
What
Points the
mcpdependency atdbt-labs/mcp-python-sdk@dbt-labs/patched, which includes:Upstream PR: modelcontextprotocol/python-sdk#2145
Notes
This is a temporary pin until the upstream PR is merged and released. Once upstream publishes a release containing the fix, we should revert to the published package.
Drafted by Claude Opus 4.6 under the direction of @wiggzz