Increasing Buffer Size in MCP stdio Transport #1143
Closed
+3
−2
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
Kludex
reviewed
Jul 15, 2025
Comment on lines
+57
to
+59
| # FIXED: Changed from 0 to 10 to create buffered streams | ||
| read_stream_writer, read_stream = anyio.create_memory_object_stream(10) | ||
| write_stream, write_stream_reader = anyio.create_memory_object_stream(10) |
There was a problem hiding this comment.
I think the idea is exactly to not have this buffer.
|
Thank you for debugging this. Lets continue the discussion in the #1141. Not having a buffer is on purpose. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Fixes: #1141
When using the low-level Server API (mcp.server.lowlevel.Server) with stdio transport, sending progress notifications during request handling causes the server to hang indefinitely and never send the final response.
This issue was discovered while implementing an MCP server that returns large SQL query results and detailed analysis. The server would hang indefinitely when the output exceeded the OS pipe buffer limit.
Motivation and Context
Provides a fix for #1141
The current stdio transport implementation uses unbuffered memory object streams (buffer size 0), which can cause deadlocks when:
How Has This Been Tested?
Tested with code shared in original #1141 and fix works in it.
Breaking Changes
No
Types of changes
Checklist