Cairn
NousResearch/hermes-agent

MCP shutdown 'Event loop is closed' RuntimeError during task cancellation

Cluster 60197 · mcp. Data as of

2 open items. Fix merged in #74139 on 29 Jul 2026. Check it covers your case.

The short answer

0open issues
2open PRs
15items grouped
Known?
Yes. 15 related items grouped here, 3 issues already closed.
Fix event
A fix was merged to main in PR #74139. Check it covers your case. No release data is tracked.
Tracker
The maintainers' tracker marks this partially resolved, deciding PR #74139. That is separate from the fix event.
Still open
0 issues and 2 PRs.

Nearly all members concern a RuntimeError ('Event loop is closed') raised when MCP server tasks are cancelled or cleaned up during /exit, Ctrl+C, or shutdown. They include bug reports and several proposed changes, such as catching the error, moving cancel() into a try block, and draining or reaping parked tasks.

Open issues0

No open issues.

Open PRs2

  • PR#60032fix(mcp): catch RuntimeError when cancelling tasks on a closed event loop
  • PR#64114fix(mcp): catch RuntimeError when canceling tasks during event loop close

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

  • #74139 fix(mcp): drain the MCP loop and retain parked startup tasks for clean shutdown

    merged to main

    files: contributors/emails/[redacted:email], contributors/emails/[redacted:email], scripts/release.py, tests/tools/test_mcp_initial_connect_shutdown.py, tests/tools/test_mcp_stability.py, tests/tools/test_mcp_tool.py, tools/mcp_tool.py

9 PRs closed without merging

From the close comments: duplicate 4 · done elsewhere 2 · superseded by another PR 2 · merged via another change 1

  • #60205 fix(mcp): catch RuntimeError when canceling tasks on closed event loop during /exit · duplicate → #60032, #60197
  • #60213 fix(mcp): move t.cancel() inside try block to prevent RuntimeError on exit (#60197) · duplicate → #60032, #60205, #60104, #60197
  • #60287 fix(mcp): move t.cancel() inside try block to prevent RuntimeError on /exit · duplicate → #60032, #60213, #60197
  • #61466 Fix MCP task cancellation after event loop shutdown · superseded by another PR → #74139, #60197
  • #69420 fix(mcp): swallow RuntimeError when cancelling parked tasks on closed loop · merged via another change → 1f70ba6, #74139, #60032
Show 4 more
  • #71846 fix(mcp): catch RuntimeError in _wait_for_reconnect_or_shutdown cleanup · done elsewhere → 1f70ba6, #74139
  • #72054 fix(mcp): reap orphaned parked server task in _connect_server · done elsewhere → #74139, #62026
  • #73190 fix(mcp): catch RuntimeError when cancelling tasks during /exit (#60197) · duplicate → #60032
  • #73765 fix(mcp): suppress 'Event loop is closed' during shutdown race · superseded by another PR → #74139, #60197
Closed issues · 3
  • Closed#60197[Bug] RuntimeError: Event loop is closed during /exit (MCPServerTask.shutdown)
  • Closed#66113RuntimeError: Event loop is closed during MCP shutdown
  • Closed#66228RuntimeError: Event loop is closed on Ctrl+C exit (MCP server shutdown race)
How this cluster was grouped
  • Link evidence (partly structural links): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.
  • Members outside that structural core may belong to a different underlying problem.
  • Pairwise link density 0.16: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. 1.00 means 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 Lab

At a glance

Subsystem
mcp
Merged PRs
#74139
Closed issues
3
Attempts
9 PRs closed without merging
Fix link checked
29 Jul 2026

For your agent

The same facts, typed.

cluster/60197.json
cluster/60197.md