Fix MCP protocol compatibility by reverting to stateless HTTP mode #582
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Outdated suggestions cannot be applied.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.
Problem
After enabling FastMCP sessions () in PR #580, Test Agent MCP endpoint began failing with "Unknown error" while A2A continued working.
Root Cause Analysis
FastMCP sessions require proper protocol flow: Session-based mode expects:
Current MCP clients don't implement session management: The ADCPClient and test scripts call tools directly without establishing sessions first
Errors occur at protocol layer: The failure happens in FastMCP's HTTP transport layer before our tool code executes, which is why no errors appear in application logs
get_http_headers() doesn't need sessions: This function works via context variables (contextvars) which FastMCP provides in both stateless and session-based modes
Solution
Revert to
stateless_http=True(the previous working state) while keeping all context safety improvements from PRs #577, #578, and #580.What This Fixes
What's Preserved
Testing
References