claude-code - 💡(How to fix) Fix [Bug] Filesystem MCP server crashes on startup with "Server transport closed unexpectedly" [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
anthropics/claude-code#49274Fetched 2026-04-17 08:45:55
View on GitHub
Comments
0
Participants
1
Timeline
4
Reactions
0
Participants
Timeline (top)
labeled ×4

Error Message

[{"error":"Error: Failed to delete keychain entry: security: SecKeychainSearchCopyNext: The specified item could not be found in the keychain.\n at vMq (file:///Users/smartepdworkaccount/.nvm/versions/node/v22.22.1/lib/node_modules/@anthropic-ai/claude-code/cli.js:301:272235)\n at process.processTicksAndRejections (node:internal/process/task_queues:103:5)\n at async BUq (file:///Users/smartepdworkaccount/.nvm/versions/node/v22.22.1/lib/node_modules/@anthropic-ai/claude-code/cli.js:480:889)\n at async eR1 (file:///Users/smartepdworkaccount/.nvm/versions/node/v22.22.1/lib/node_modules/@anthropic-ai/claude-code/cli.js:480:787)\n at async pq8 (file:///Users/smartepdworkaccount/.nvm/versions/node/v22.22.1/lib/node_modules/@anthropic-ai/claude-code/cli.js:2986:2123)\n at async fX6 (file:///Users/smartepdworkaccount/.nvm/versions/node/v22.22.1/lib/node_modules/@anthropic-ai/claude-code/cli.js:3011:5687)\n at async file:///Users/smartepdworkaccount/.nvm/versions/node/v22.22.1/lib/node_modules/@anthropic-ai/claude-code/cli.js:3035:3250","timestamp":"2026-04-16T16:48:42.109Z"},{"error":"RangeError [ERR_CHILD_PROCESS_STDIO_MAXBUFFER]: stdout maxBuffer length exceeded\n at Socket.onChildStdout (node:child_process:484:14)\n at Socket.emit (node:events:519:28)\n at addChunk (node:internal/streams/readable:561:12)\n at readableAddChunkPushByteMode (node:internal/streams/readable:512:3)\n at Readable.push (node:internal/streams/readable:392:5)\n at Pipe.onStreamRead (node:internal/stream_base_commons:189:23)","timestamp":"2026-04-16T16:49:17.741Z"}]

Code Example

[{"error":"Error: Failed to delete keychain entry: security: SecKeychainSearchCopyNext: The specified item could not be found in the keychain.\n    at vMq (file:///Users/smartepdworkaccount/.nvm/versions/node/v22.22.1/lib/node_modules/@anthropic-ai/claude-code/cli.js:301:272235)\n    at process.processTicksAndRejections (node:internal/process/task_queues:103:5)\n    at async BUq (file:///Users/smartepdworkaccount/.nvm/versions/node/v22.22.1/lib/node_modules/@anthropic-ai/claude-code/cli.js:480:889)\n    at async eR1 (file:///Users/smartepdworkaccount/.nvm/versions/node/v22.22.1/lib/node_modules/@anthropic-ai/claude-code/cli.js:480:787)\n    at async pq8 (file:///Users/smartepdworkaccount/.nvm/versions/node/v22.22.1/lib/node_modules/@anthropic-ai/claude-code/cli.js:2986:2123)\n    at async fX6 (file:///Users/smartepdworkaccount/.nvm/versions/node/v22.22.1/lib/node_modules/@anthropic-ai/claude-code/cli.js:3011:5687)\n    at async file:///Users/smartepdworkaccount/.nvm/versions/node/v22.22.1/lib/node_modules/@anthropic-ai/claude-code/cli.js:3035:3250","timestamp":"2026-04-16T16:48:42.109Z"},{"error":"RangeError [ERR_CHILD_PROCESS_STDIO_MAXBUFFER]: stdout maxBuffer length exceeded\n    at Socket.onChildStdout (node:child_process:484:14)\n    at Socket.emit (node:events:519:28)\n    at addChunk (node:internal/streams/readable:561:12)\n    at readableAddChunkPushByteMode (node:internal/streams/readable:512:3)\n    at Readable.push (node:internal/streams/readable:392:5)\n    at Pipe.onStreamRead (node:internal/stream_base_commons:189:23)","timestamp":"2026-04-16T16:49:17.741Z"}]
RAW_BUFFERClick to expand / collapse

Bug Description I've been experiencing issues with Cowork (desktop app on Mac) since the outage on April 15. Even after a full Mac restart, I'm unable to add folders and keep getting two errors: "Session VM process not available. The session may not be fully initialized." "Failed to mount [folder path] – operation not permitted" Looking at the MCP logs, the Filesystem server is crashing almost immediately after every startup with "Server transport closed unexpectedly" — it never stays connected long enough to complete initialization. This was working fine for weeks prior. I've attached the relevant logs. Could you please investigate and reset my session? Account email: [email protected]

Environment Info

  • Platform: darwin
  • Terminal: Apple_Terminal
  • Version: 2.1.111
  • Feedback ID: 14bf7419-1a4c-4584-9e30-44d87fe78b90

Errors

[{"error":"Error: Failed to delete keychain entry: security: SecKeychainSearchCopyNext: The specified item could not be found in the keychain.\n    at vMq (file:///Users/smartepdworkaccount/.nvm/versions/node/v22.22.1/lib/node_modules/@anthropic-ai/claude-code/cli.js:301:272235)\n    at process.processTicksAndRejections (node:internal/process/task_queues:103:5)\n    at async BUq (file:///Users/smartepdworkaccount/.nvm/versions/node/v22.22.1/lib/node_modules/@anthropic-ai/claude-code/cli.js:480:889)\n    at async eR1 (file:///Users/smartepdworkaccount/.nvm/versions/node/v22.22.1/lib/node_modules/@anthropic-ai/claude-code/cli.js:480:787)\n    at async pq8 (file:///Users/smartepdworkaccount/.nvm/versions/node/v22.22.1/lib/node_modules/@anthropic-ai/claude-code/cli.js:2986:2123)\n    at async fX6 (file:///Users/smartepdworkaccount/.nvm/versions/node/v22.22.1/lib/node_modules/@anthropic-ai/claude-code/cli.js:3011:5687)\n    at async file:///Users/smartepdworkaccount/.nvm/versions/node/v22.22.1/lib/node_modules/@anthropic-ai/claude-code/cli.js:3035:3250","timestamp":"2026-04-16T16:48:42.109Z"},{"error":"RangeError [ERR_CHILD_PROCESS_STDIO_MAXBUFFER]: stdout maxBuffer length exceeded\n    at Socket.onChildStdout (node:child_process:484:14)\n    at Socket.emit (node:events:519:28)\n    at addChunk (node:internal/streams/readable:561:12)\n    at readableAddChunkPushByteMode (node:internal/streams/readable:512:3)\n    at Readable.push (node:internal/streams/readable:392:5)\n    at Pipe.onStreamRead (node:internal/stream_base_commons:189:23)","timestamp":"2026-04-16T16:49:17.741Z"}]

extent analysis

TL;DR

The issue may be resolved by resetting the session and checking the Filesystem server connection.

Guidance

  • Investigate the "Server transport closed unexpectedly" error in the MCP logs to determine the cause of the Filesystem server crashing.
  • Check the keychain entry deletion error and its relation to the session initialization issue.
  • Verify the Node.js version and its compatibility with the Cowork app.
  • Review the attached logs for any additional error messages or clues.

Example

No specific code snippet can be provided without further information on the Cowork app's internal workings.

Notes

The issue seems to be related to the Filesystem server connection and session initialization. However, without more information on the Cowork app's architecture and the MCP logs, it's difficult to provide a more specific solution.

Recommendation

Apply a workaround by resetting the session and checking the Filesystem server connection, as this may resolve the issue temporarily until a more permanent fix can be found.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING