MCP stdio subprocess reliability and unrelated bug
Cluster 96497 · mcp. Data as of
1 open item. Fix merged in #100987 on 2 Sep 2026. Check it covers your case.
The short answer
- Known?
- Yes. 3 related items grouped here, 0 issues already closed.
- Fix event
- A fix was merged to main in PR #100987. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
unresolved. That is separate from the fix event. - Still open
- 1 issue and 0 PRs.
Next step: read #100987, then check whether your report is the one still open.
Read #100987Pick up a Lab taskTwo related fixes address MCP stdio tool calls failing when a subprocess exits, covering respawn/retry logic and Linux child-PID tracking. The third item ('Azure devs') is unrelated and too vague to characterize.
Open issues1
- Issue#96497[Bug]: Azure devs
Open PRs0
Fixes on record
-
#100987 fix(mcp): stdio tool calls survive a dead subprocess — respawn+retry, and Linux child-PID tracking actually works (salvage #100814)
files:
contributors/emails/[redacted:email],tests/tools/test_mcp_stability.py,tests/tools/test_mcp_stdio_fastfail_reconnect.py,tools/mcp_tool.py
1 PR closed without merging
From the close comments: done elsewhere 1
-
#96510 fix(mcp): keep stdio tools working after subprocess exits · done elsewhere →
b828624,696d854,#100987,#100814
How this cluster was grouped
-
Link evidence (
structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference. -
Pairwise link density
0.67: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36.1.00means every pair is linked.
Pick up a Lab task
Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.
Open the LabAt a glance
- Subsystem
- mcp
- Merged PRs
- #100987
- Closed issues
- 0
- Attempts
- 1 PR closed without merging
- Fix link checked
- 2 Sep 2026