MCP keepalive wrongly respawns stdio servers on silent ping
Cluster 97245. Data as of
Nothing open on GitHub. Fix merged in #101025 on 2 Sep 2026. Check it covers your case.
The short answer
- Known?
- Yes. 4 related items grouped here, 1 issue already closed.
- Fix event
- A fix was merged to main in PR #101025. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
resolved, deciding PR #101025. That is separate from the fix event. - Still open
- Nothing open on GitHub.
A bug where the MCP keepalive mechanism incorrectly treats a stdio server's silent dropping of ping messages as a dead transport, triggering unnecessary respawns. Multiple fix attempts address distinguishing silent ping drops from actual transport failures.
Open issues0
Open PRs0
Fixes on record
-
#101025 fix(mcp): keepalive no longer respawns a healthy stdio server that silently drops ping (#97245, salvage #97258)
files:
tests/tools/test_mcp_capability_gating.py,tools/mcp_tool.py
2 PRs closed without merging
From the close comments: done elsewhere 1 · other 1
Closed issues · 1
- Closed#97245MCP keepalive respawn-loops a healthy stdio server that never answers ping (silent drop ≠ -32601)
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structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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
0.50: 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
- Merged PRs
- #101025
- Closed issues
- 1
- Attempts
- 2 PRs closed without merging
- Fix link checked
- 2 Sep 2026