BUG: MCP servers fail to connect in Claude Code despite correct configuration

[GratefulDave]

Bug Description Operating System: macOS Darwin 24.5.0

Node.js Version: v23.10.0 (via nvm)

Issue Description: MCP servers consistently fail to connect in Claude Code, even though they are properly configured and the servers themselves work correctly when tested independently.

Steps to Reproduce:

1. Install MCP server globally: npm install -g @modelcontextprotocol/server-filesystem
2. Add MCP server to Claude Code: claude mcp add filesystem "npx" "@modelcontextprotocol/server-filesystem" "/Users/username/Projects/"
3. Verify server is listed: claude mcp list

Output shows: filesystem: npx @modelcontextprotocol/server-filesystem /Users/username/Projects/

4. Start Claude Code: claude
5. Attempt to use MCP tools - all fail with "MCP servers failed to connect"

Expected Behavior: MCP servers should connect and be available for use within Claude Code.

Actual Behavior: All MCP servers fail to connect, despite being properly configured and working when tested independently.

Additional Information:

1. The MCP server works correctly when tested directly: echo '{"jsonrpc":"2.0","method":"initialize","params":{"protocolVersion":"2024-11-05","clientInfo":{"name":"test","version":"1.0.0"},"capabilities":{}},"id":1}' | npx @modelcontextprotocol/server-filesystem /path/to/directory
2. Returns successful initialization response.
3. Tried multiple configuration approaches: - Using npx with -y flag - Using direct node path with full path to server - Creating .mcp.json in project directory - Using --mcp-config flag with JSON file - Importing from Claude Desktop config
4. No error logs are generated in any standard log locations.
5. The same configuration works in Claude Desktop app but fails in Claude Code CLI.

Environment Details:

• Multiple MCP servers tested (filesystem, memory, github, etc.)
• All exhibit the same connection failure
• No permission issues (all files have correct permissions)
• PATH includes node/npm directories

This appears to be a fundamental issue with Claude Code's MCP integration rather than a configuration problem, as the servers work correctly outside of Claude Code.

Environment Info

• Platform: macos
• Terminal: pycharm
• Version: 1.0.11
• Feedback ID: 74d37a8d-973a-43c3-96ea-e43aa60b7888

Errors

[{"error":"AbortError: The operation was aborted\n    at abortChildProcess (node:child_process:716:27)\n    at onAbortListener (node:child_process:786:7)\n    at process.processTicksAndRejections (node:internal/process/task_queues:85:11)","timestamp":"2025-06-04T23:03:51.295Z"},{"error":"Error: Command failed: security find-generic-password -a $USER -w -s \"Claude Code\"\nsecurity: SecKeychainSearchCopyNext: The specified item could not be found in the keychain.\n\n    at genericNodeError (node:internal/errors:983:15)\n    at wrappedFn (node:internal/errors:537:14)\n    at checkExecSyncError (node:child_process:882:11)\n    at execSync (node:child_process:954:15)\n    at JZ (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:683:2402)\n    at file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:582:11763\n    at Q (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:526:17069)\n    at LU (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:582:10909)\n    at HG (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:582:10355)\n    at lO2 (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:2042:4758)","timestamp":"2025-06-04T23:03:51.321Z"},{"error":"Error: No logs found at /Users/davidandrews/Library/Caches/claude-cli-nodejs/-Users-davidandrews-PycharmProjects-lexgenius/messages\n    at tT4 (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:583:3738)\n    at iQ1 (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:583:3487)\n    at OAA.<anonymous> (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:2337:2015)\n    at process.processTicksAndRejections (node:internal/process/task_queues:105:5)\n    at async OAA.parseAsync (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:517:4184)\n    at async vE5 (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:2340:5983)\n    at async xE5 (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:2336:17530)","timestamp":"2025-06-04T23:03:51.349Z"},{"error":"AbortError: The operation was aborted\n    at abortChildProcess (node:child_process:716:27)\n    at AbortSignal.onAbortListener (node:child_process:786:7)\n    at [nodejs.internal.kHybridDispatch] (node:internal/event_target:827:20)\n    at AbortSignal.dispatchEvent (node:internal/event_target:762:26)\n    at runAbort (node:internal/abort_controller:449:10)\n    at abortSignal (node:internal/abort_controller:435:3)\n    at AbortController.abort (node:internal/abort_controller:468:5)\n    at Timeout._onTimeout (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:2336:15943)\n    at listOnTimeout (node:internal/timers:611:17)\n    at process.processTimers (node:internal/timers:546:7)","timestamp":"2025-06-04T23:03:54.232Z"},{"error":"ShellError: Shell command failed\n    at Object.call (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:1547:1326)\n    at process.processTicksAndRejections (node:internal/process/task_queues:105:5)\n    at async pZ5 (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:1889:19078)\n    at async YK1 (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:1889:17664)\n    at async dZ5 (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:1889:16706)\n    at async hZ5 (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:1889:16356)\n    at async oe (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:1889:15392)\n    at async oe (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:1889:16218)\n    at async oe (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:1889:16218)\n    at async oe (file:///Users/davidandrews/.nvm/versions/node/v23.10.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:1889:16218)","timestamp":"2025-06-04T23:05:14.363Z"},{"error":"ShellError: Shell command failed\n    at Object.call (file:///Users/davidandrews/.nvm/versions/nod

Note: Error logs were truncated.

[afsheee]

was this fixed? i'm still having issues with claude code connecting to supabase mcp

[leaanthony]

Same issue for basically any mcp server

[banditFox]

Experiencing the same issue. Restarting Claude several times and eventually it connects. But it's almost like the MCP server needs to be 'warmed up'?

A restart of claude, initiazes the app but page is blank. Go to settings, then closing settings, and then the page populates.

macOS: Sequoia 15.5 node version v22.16.0

UPDATE: Ok, folks. So some complexity here.

1. I had Node installed but npm was installed globally so npm --version would returned a 'not recognized'.
2. I did not have the location of npm.
3. Re-installed npm (kinda) and added the path to my ~.zshrc

I'm still testing, but so far seems like it's working much faster and bettah.

In short;

1. Make sure npm is running locally.
2. Make sure ~.zshrc has the 'export NVM_DIR="$HOME/ .nvm" in the config.
3. Shut down iTerm, shut-down Claude Desktop. and fire everything back up. Should work.

[vishwa-prabhath]

I have the same issue .I just had the demo server code in demo server python sdk . It also give me cant connect to the mcp server. Any suggestions?

[ashwin-ant]

Can you try running claude --debug to see if anything is displayed?

[vishwa-prabhath]

i tried to but i cant get to run claude debug .cli is not found and I dont think its the issue since im using python sdk.

[edbyford]

Having the same problem with a couple of MCP servers.

[pjgoodall]

wasted hours trying to get gitea MCP working with claude-code

[timjrobinson]

I'm also seeing this. The MCP server works fine in Claude Desktop but Claude Code can't find any tools for it

[seanmozeik]

Having the same issue - It will work fine for a few tool uses, and then spontaneously disconnect and can't reconnect with restarting claude code, sometimes a few times. MacOS.

[Kaddtechnologies]

This is still an issue and a very breaking issue. It should be prioritized

[ashwin-ant]

Hey all, I'm trying to understand all of the reports here. Is this a single issue or are there multiple things going on here?

@timjrobinson can you share more about the server config you're using? Does the server show as connected in /mcp but says it has no tools when you drill into the details?

@seanmozeik are you using stdio servers or remote servers? Or is this for any server?

If anyone is able to run with claude --debug and share output from that, that'll really help. You can also find MCP logs in ~/Library/Caches/claude-cli-nodejs/ (within different subdirectories there).

[Kaddtechnologies]

Mine just timeout after the limit is reached . The Servers work fine on Claude Desktop. I import them over to claude code using claude mcp add-from-claude-desktop command.

Sometimes the servers work in Claude Code, other times more often than not they just dont work. Very buggy

[DEBUG] MCP server "mcp-server-firecrawl": Connection failed: Error: Connection to MCP server "mcp-server-firecrawl" timed out after 30000ms [DEBUG] MCP server "mcp-server-firecrawl": Error message: Connection to MCP server "mcp-server-firecrawl" timed out after 30000ms [DEBUG] MCP server "mcp-server-firecrawl": Error stack: Error: Connection to MCP server "mcp-server-firecrawl" timed out after 30000ms at Timeout._onTimeout (file:///home/username/.nvm/versions/node/v22.16.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:1383:5751) at listOnTimeout (node:internal/timers:588:17) at process.processTimers (node:internal/timers:523:7) ╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮ [DEBUG] MCP server "firebase-mcp": Connection failed: Error: Connection to MCP server "firebase-mcp" timed out after 30000ms [DEBUG] MCP server "firebase-mcp": Error message: Connection to MCP server "firebase-mcp" timed out after 30000ms [DEBUG] MCP server "firebase-mcp": Error stack: Error: Connection to MCP server "firebase-mcp" timed out after 30000ms at Timeout._onTimeout (file:///home/username/.nvm/versions/node/v22.16.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:1383:5751) at listOnTimeout (node:internal/timers:588:17) at process.processTimers (node:internal/timers:523:7) ╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮ [DEBUG] MCP server "playwright": Connection failed: Error: Connection to MCP server "playwright" timed out after 30000ms [DEBUG] MCP server "playwright": Error message: Connection to MCP server "playwright" timed out after 30000ms [DEBUG] MCP server "playwright": Error stack: Error: Connection to MCP server "playwright" timed out after 30000ms at Timeout._onTimeout (file:///home/username/.nvm/versions/node/v22.16.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:1383:5751) at listOnTimeout (node:internal/timers:588:17) at process.processTimers (node:internal/timers:523:7) ╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮ [DEBUG] MCP server "youtube-transcript": Connection failed: Error: Connection to MCP server "youtube-transcript" timed out after 30000ms [DEBUG] MCP server "youtube-transcript": Error message: Connection to MCP server "youtube-transcript" timed out after 30000ms [DEBUG] MCP server "youtube-transcript": Error stack: Error: Connection to MCP server "youtube-transcript" timed out after 30000ms at Timeout._onTimeout (file:///home/username/.nvm/versions/node/v22.16.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:1383:5751) at listOnTimeout (node:internal/timers:588:17) at process.processTimers (node:internal/timers:523:7) ╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮ [DEBUG] MCP server "ElevenLabs": Connection failed: Error: Connection to MCP server "ElevenLabs" timed out after 30000ms [DEBUG] MCP server "ElevenLabs": Error message: Connection to MCP server "ElevenLabs" timed out after 30000ms [DEBUG] MCP server "ElevenLabs": Error stack: Error: Connection to MCP server "ElevenLabs" timed out after 30000ms at Timeout._onTimeout (file:///home/username/.nvm/versions/node/v22.16.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:1383:5751) at listOnTimeout (node:internal/timers:588:17) at process.processTimers (node:internal/timers:523:7) ╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮[DEBUG] MCP server "qdrant": Connection failed: Error: Connection to MCP server "qdrant" timed out after 30000ms [DEBUG] MCP server "qdrant": Error message: Connection to MCP server "qdrant" timed out after 30000ms [DEBUG] MCP server "qdrant": Error stack: Error: Connection to MCP server "qdrant" timed out after 30000ms at Timeout._onTimeout (file:///home/username/.nvm/versions/node/v22.16.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:1383:5751) at listOnTimeout (node:internal/timers:588:17) at process.processTimers (node:internal/timers:523:7) ╭────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮ [DEBUG] MCP server "postgres": Connection failed: Error: Connection to MCP server "postgres" timed out after 30000ms [DEBUG] MCP server "postgres": Error message: Connection to MCP server "postgres" timed out after 30000ms [DEBUG] MCP server "postgres": Error stack: Error: Connection to MCP server "postgres" timed out after 30000ms at Timeout._onTimeout (file:///home/username/.nvm/versions/node/v22.16.0/lib/node_modules/@anthropic-ai/claude-code/cli.js:1383:5751) at listOnTimeout (node:internal/timers:588:17) at process.processTimers (node:internal/timers:523:7)

[timjrobinson]

@ashwin-ant the MCP server has started working for me again after adding it in Claude code explicitly with claude mcp add it can see the tools. Previously when using the claude file from claude desktop it wasn't working (I guess code and desktop use different configs and I didn't realize?)

[ZachHandley]

Can confirm I also have this issue with FastMCP stdio transport. I've been trying this for a while, I've wrapped calls and a lot more, but for whatever reason it really struggles.

[ERROR] MCP server "claude-mcp-orchestration" Server stderr: {"event": "    + Exception Group Traceback (most recent call last):", "timestamp": "2025-07-07T01:26:24.151820Z"}
[ERROR] MCP server "claude-mcp-orchestration" Server stderr: {"event": "    |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/claude_mcp_tools/orchestration_server.py\", line 1918, in main", "timestamp": "2025-07-07T01:26:24.151866Z"}
{"event": "    |     app.run()", "timestamp": "2025-07-07T01:26:24.151888Z"}
{"event": "    |     ~~~~~~~^^", "timestamp": "2025-07-07T01:26:24.151901Z"}
{"event": "    |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/fastmcp/server/server.py\", line 328, in run", "timestamp": "2025-07-07T01:26:24.151913Z"}
{"event": "    |     anyio.run(", "timestamp": "2025-07-07T01:26:24.151922Z"}
{"event": "    |     ~~~~~~~~~^", "timestamp": "2025-07-07T01:26:24.151929Z"}
{"event": "    |         partial(", "timestamp": "2025-07-07T01:26:24.151937Z"}
{"event": "    |         ^^^^^^^^", "timestamp": "2025-07-07T01:26:24.151945Z"}
{"event": "    |     ...<4 lines>...", "timestamp": "2025-07-07T01:26:24.151952Z"}
{"event": "    |         )", "timestamp": "2025-07-07T01:26:24.151960Z"}
{"event": "    |         ^", "timestamp": "2025-07-07T01:26:24.151967Z"}
{"event": "    |     )", "timestamp": "2025-07-07T01:26:24.151974Z"}
{"event": "    |     ^", "timestamp": "2025-07-07T01:26:24.151982Z"}
{"event": "    |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/anyio/_core/_eventloop.py\", line 74, in run", "timestamp": "2025-07-07T01:26:24.151989Z"}
{"event": "    |     return async_backend.run(func, args, {}, backend_options)", "timestamp": "2025-07-07T01:26:24.151997Z"}
{"event": "    |            ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^", "timestamp": "2025-07-07T01:26:24.152004Z"}
{"event": "    |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/anyio/_backends/_asyncio.py\", line 2310, in run", "timestamp": "2025-07-07T01:26:24.152011Z"}
{"event": "    |     return runner.run(wrapper())", "timestamp": "2025-07-07T01:26:24.152019Z"}
{"event": "    |            ~~~~~~~~~~^^^^^^^^^^^", "timestamp": "2025-07-07T01:26:24.152026Z"}
{"event": "    |   File \"/home/zach/.local/share/uv/python/cpython-3.13.1-linux-x86_64-gnu/lib/python3.13/asyncio/runners.py\", line 118, in run", "timestamp": "2025-07-07T01:26:24.152033Z"}
{"event": "    |     return self._loop.run_until_complete(task)", "timestamp": "2025-07-07T01:26:24.152041Z"}
{"event": "    |            ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^", "timestamp": "2025-07-07T01:26:24.152048Z"}
{"event": "    |   File \"uvloop/loop.pyx\", line 1518, in uvloop.loop.Loop.run_until_complete", "timestamp": "2025-07-07T01:26:24.152055Z"}
{"event": "    |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/anyio/_backends/_asyncio.py\", line 2298, in wrapper", "timestamp": "2025-07-07T01:26:24.152063Z"}
{"event": "    |     return await func(*args)", "timestamp": "2025-07-07T01:26:24.152070Z"}
{"event": "    |            ^^^^^^^^^^^^^^^^^", "timestamp": "2025-07-07T01:26:24.152077Z"}
{"event": "    |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/fastmcp/server/server.py\", line 303, in run_async", "timestamp": "2025-07-07T01:26:24.152085Z"}
{"event": "    |     await self.run_stdio_async(", "timestamp": "2025-07-07T01:26:24.152092Z"}
{"event": "    |     ...<2 lines>...", "timestamp": "2025-07-07T01:26:24.152099Z"}
{"event": "    |     )", "timestamp": "2025-07-07T01:26:24.152108Z"}
{"event": "    |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/fastmcp/server/server.py\", line 1351, in run_stdio_async", "timestamp": "2025-07-07T01:26:24.152116Z"}
{"event": "    |     async with stdio_server() as (read_stream, write_stream):", "timestamp": "2025-07-07T01:26:24.152126Z"}
{"event": "    |                ~~~~~~~~~~~~^^", "timestamp": "2025-07-07T01:26:24.152136Z"}
{"event": "    |   File \"/home/zach/.local/share/uv/python/cpython-3.13.1-linux-x86_64-gnu/lib/python3.13/contextlib.py\", line 235, in __aexit__", "timestamp": "2025-07-07T01:26:24.152146Z"}
{"event": "    |     await self.gen.athrow(value)", "timestamp": "2025-07-07T01:26:24.152155Z"}
{"event": "    |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/mcp/server/stdio.py\", line 85, in stdio_server", "timestamp": "2025-07-07T01:26:24.152165Z"}
{"event": "    |     async with anyio.create_task_group() as tg:", "timestamp": "2025-07-07T01:26:24.152201Z"}
{"event": "    |                ~~~~~~~~~~~~~~~~~~~~~~~^^", "timestamp": "2025-07-07T01:26:24.152213Z"}
{"event": "    |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/anyio/_backends/_asyncio.py\", line 772, in __aexit__", "timestamp": "2025-07-07T01:26:24.152223Z"}
{"event": "    |     raise BaseExceptionGroup(", "timestamp": "2025-07-07T01:26:24.152232Z"}
{"event": "    |         \"unhandled errors in a TaskGroup\", self._exceptions", "timestamp": "2025-07-07T01:26:24.152239Z"}
{"event": "    |     ) from None", "timestamp": "2025-07-07T01:26:24.152247Z"}
{"event": "    | ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception)", "timestamp": "2025-07-07T01:26:24.152256Z"}
{"event": "    +-+---------------- 1 ----------------", "timestamp": "2025-07-07T01:26:24.152263Z"}
{"event": "      | Exception Group Traceback (most recent call last):", "timestamp": "2025-07-07T01:26:24.152271Z"}
{"event": "      |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/mcp/server/stdio.py\", line 88, in stdio_server", "timestamp": "2025-07-07T01:26:24.152279Z"}
{"event": "      |     yield read_stream, write_stream", "timestamp": "2025-07-07T01:26:24.152287Z"}
{"event": "      |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/fastmcp/server/server.py\", line 1353, in run_stdio_async", "timestamp": "2025-07-07T01:26:24.152295Z"}
{"event": "      |     await self._mcp_server.run(", "timestamp": "2025-07-07T01:26:24.152303Z"}
{"event": "      |     ...<5 lines>...", "timestamp": "2025-07-07T01:26:24.152311Z"}
{"event": "      |     )", "timestamp": "2025-07-07T01:26:24.152318Z"}
{"event": "      |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/mcp/server/lowlevel/server.py\", line 569, in run", "timestamp": "2025-07-07T01:26:24.152326Z"}
{"event": "      |     async with AsyncExitStack() as stack:", "timestamp": "2025-07-07T01:26:24.152334Z"}
{"event": "      |                ~~~~~~~~~~~~~~^^", "timestamp": "2025-07-07T01:26:24.152341Z"}
{"event": "      |   File \"/home/zach/.local/share/uv/python/cpython-3.13.1-linux-x86_64-gnu/lib/python3.13/contextlib.py\", line 768, in __aexit__", "timestamp": "2025-07-07T01:26:24.152362Z"}
{"event": "      |     raise exc", "timestamp": "2025-07-07T01:26:24.152380Z"}
{"event": "      |   File \"/home/zach/.local/share/uv/python/cpython-3.13.1-linux-x86_64-gnu/lib/python3.13/contextlib.py\", line 751, in __aexit__", "timestamp": "2025-07-07T01:26:24.152391Z"}
{"event": "      |     cb_suppress = await cb(*exc_details)", "timestamp": "2025-07-07T01:26:24.152401Z"}
{"event": "      |                   ^^^^^^^^^^^^^^^^^^^^^^", "timestamp": "2025-07-07T01:26:24.152411Z"}
{"event": "      |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/mcp/shared/session.py\", line 218, in __aexit__", "timestamp": "2025-07-07T01:26:24.152420Z"}
{"event": "      |     return await self._task_group.__aexit__(exc_type, exc_val, exc_tb)", "timestamp": "2025-07-07T01:26:24.152428Z"}
{"event": "      |            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^", "timestamp": "2025-07-07T01:26:24.152436Z"}
{"event": "      |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/anyio/_backends/_asyncio.py\", line 772, in __aexit__", "timestamp": "2025-07-07T01:26:24.152444Z"}
{"event": "      |     raise BaseExceptionGroup(", "timestamp": "2025-07-07T01:26:24.152451Z"}
{"event": "      |         \"unhandled errors in a TaskGroup\", self._exceptions", "timestamp": "2025-07-07T01:26:24.152459Z"}
{"event": "      |     ) from None", "timestamp": "2025-07-07T01:26:24.152467Z"}
{"event": "      | ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception)", "timestamp": "2025-07-07T01:26:24.152475Z"}
{"event": "      +-+---------------- 1 ----------------", "timestamp": "2025-07-07T01:26:24.152483Z"}
{"event": "        | Exception Group Traceback (most recent call last):", "timestamp": "2025-07-07T01:26:24.152490Z"}
[ERROR] MCP server "claude-mcp-orchestration" Server stderr: {"event": "        |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/mcp/server/lowlevel/server.py\", line 580, in run", "timestamp": "2025-07-07T01:26:24.152498Z"}
{"event": "        |     async with anyio.create_task_group() as tg:", "timestamp": "2025-07-07T01:26:24.152506Z"}
{"event": "        |                ~~~~~~~~~~~~~~~~~~~~~~~^^", "timestamp": "2025-07-07T01:26:24.152514Z"}
{"event": "        |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/anyio/_backends/_asyncio.py\", line 772, in __aexit__", "timestamp": "2025-07-07T01:26:24.152521Z"}
{"event": "        |     raise BaseExceptionGroup(", "timestamp": "2025-07-07T01:26:24.152529Z"}
{"event": "        |         \"unhandled errors in a TaskGroup\", self._exceptions", "timestamp": "2025-07-07T01:26:24.152536Z"}
{"event": "        |     ) from None", "timestamp": "2025-07-07T01:26:24.152544Z"}
{"event": "        | ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception)", "timestamp": "2025-07-07T01:26:24.152551Z"}
{"event": "        +-+---------------- 1 ----------------", "timestamp": "2025-07-07T01:26:24.152558Z"}
{"event": "          | Traceback (most recent call last):", "timestamp": "2025-07-07T01:26:24.152566Z"}
{"event": "          |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/mcp/server/lowlevel/server.py\", line 604, in _handle_message", "timestamp": "2025-07-07T01:26:24.152573Z"}
{"event": "          |     await self._handle_request(message, req, session, lifespan_context, raise_exceptions)", "timestamp": "2025-07-07T01:26:24.152581Z"}
{"event": "          |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/mcp/server/lowlevel/server.py\", line 653, in _handle_request", "timestamp": "2025-07-07T01:26:24.152589Z"}
{"event": "          |     await message.respond(response)", "timestamp": "2025-07-07T01:26:24.152596Z"}
{"event": "          |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/mcp/shared/session.py\", line 131, in respond", "timestamp": "2025-07-07T01:26:24.152603Z"}
{"event": "          |     await self._session._send_response(  # type: ignore[reportPrivateUsage]", "timestamp": "2025-07-07T01:26:24.152611Z"}
{"event": "          |         request_id=self.request_id, response=response", "timestamp": "2025-07-07T01:26:24.152618Z"}
{"event": "          |     )", "timestamp": "2025-07-07T01:26:24.152626Z"}
{"event": "          |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/mcp/shared/session.py\", line 329, in _send_response", "timestamp": "2025-07-07T01:26:24.152633Z"}
{"event": "          |     await self._write_stream.send(session_message)", "timestamp": "2025-07-07T01:26:24.152640Z"}
{"event": "          |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/anyio/streams/memory.py\", line 242, in send", "timestamp": "2025-07-07T01:26:24.152648Z"}
{"event": "          |     self.send_nowait(item)", "timestamp": "2025-07-07T01:26:24.152655Z"}
{"event": "          |     ~~~~~~~~~~~~~~~~^^^^^^", "timestamp": "2025-07-07T01:26:24.152663Z"}
{"event": "          |   File \"/home/zach/.local/share/uv/tools/claude-mcp-tools/lib/python3.13/site-packages/anyio/streams/memory.py\", line 211, in send_nowait", "timestamp": "2025-07-07T01:26:24.152670Z"}
{"event": "          |     raise ClosedResourceError", "timestamp": "2025-07-07T01:26:24.15

this is Python FastMCP, but it is consistently happening in my package with Claude Code, and then the entire MCP server crashes after, which is the real issue, because then I can't use it. Not sure if it's directly connected, but I would love to contribute to a fix

[AndyDavo]

I'm running claude code on wsl and claude seems to intermitently detect or fail to detect by project scoped mcp's in .mcp.json. This is a pain as i want to keep my MCP config project scoped and stored with the project in github

[nishanthcgit]

The filesystem mcp, probably one of the most widely used ones still refuses to connect.. I love Claude Code but this breaking constantly is very annoying.

[byPawel]

did update to. v1.0.44, and all my 11 mcps stopped working instantly, even the custom ones, also claude code started crashing on "escape" but i can see there are other issues mentioning this

[mrjthethird]

I have the same issue, running in WSL with MCPs for Supabase and Context7 on a NextJS project. Gemini CLI works fine and Claude code works fine in other projects.

[john-savepoint]

Im sorry but this MCP thing needs to be sorted out. The MCP concept is great but I've rarely seen a tech so poorly handled, this is on par with javascript libraries in the 10s. MCP is a mess. It is unreliable, every vendor has a different implementation. Its frankly too annoying, and Anthropic has the least excuses to be getting this wrong still.

Not only do they make it ridiculously annoying on Claude Code and Claude Desktop but its not rock solid. CLine and Roo have MCP marketplace, one click and install. ANd its mostly working fine. I need CC and CD, but I also need reliable and easy MCP.

For the love of god, stop making new features and make the basics work reliably please.

[pjgoodall]

I hope Claude isn’t writing the MCP code 😢 Shoddy work. Very very expensive. No motivation to cache parses which burn up all my tokens.

[garretttaco]

Also experiencing this issue with MCPs not available in Claude code. Any updates on a fix here?

[AndyDavo]

I'm on v1.0.44 - I've just moved the scope of my MCP's from project to user and that has worked - not ideal, but at least they work

[ashwin-ant]

We're investigating a potential fix. Some questions:

• Is this strictly happening to people with multiple MCP servers? How many do you have?
• Are the servers configured as npx commands or as local node/docker commands? Or a mix? It sounds like it's both, but want to make sure.

[mrjthethird]

We're investigating a potential fix. Some questions:

• Is this strictly happening to people with multiple MCP servers? How many do you have?
• Are the servers configured as npx commands or as local node/docker commands? Or a mix? It sounds like it's both, but want to make sure.

Multiple MCP servers some at users level, some at project level in .mcp.json configured with NPX commands. @AndyDavo suggestion worked for me

[geegonzalez]

We're investigating a potential fix. Some questions:

• Is this strictly happening to people with multiple MCP servers? How many do you have?
• Are the servers configured as npx commands or as local node/docker commands? Or a mix? It sounds like it's both, but want to make sure.

I just installed Claude Code today; also getting the mcp failure to connect. I had these two:

"xcode-build": {
  "command": "npx",
  "args": [
    "-y",
    "@cameroncooke/xcode-build-mcp"
  ],
  "env": {}
},
"apple-doc-mcp": {
  "type": "stdio",
  "command": "/Users/ggonz/Developer/apple-doc-mcp",
  "args": [],
  "env": {}
}

It's still not working if I remove either one and try with just one.

[banditFox]

I have the following; Mostly it's working fine.

1. Occassionally when I fire up Claude I will have a blank Claude window.
2. if I click 'settings' in Claude, then close settings the page will load.
3. Occassionally one or more of the MCP servers don't fire up.
4. in the event #3 occurs, I shutdown Claude then it seems the MCP's fire up.

I have a;

1. filesystem mcp pointing to 3 directories.
2. puppeteer mcp
3. github mcp
4. obsidian mcp pointing to vault 1
5. another obsidian mcp pointing to vault 2

I also have all the bells and whistled turned on; IE

1. Extended Thinking
2. Web search
3. google drive search
4. gmail search
5. calendar search
6. Atlassian

Here is the error from the mcp-server log for one of my obsidian mcp's. I'm guessing a caching problem but not sure. I'm also getting a message to upgrade npm but at this point I'm kinda afraid to. Current version: 10.9.2

2025-07-10T14:58:42.412Z [mcp-obsidian-linnaean] [info] Server started and connected successfully { metadata: undefined } 2025-07-10T14:58:42.416Z [mcp-obsidian-linnaean] [info] Message from client: {"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"claude-ai","version":"0.1.0"}},"jsonrpc":"2.0","id":0} { metadata: undefined } npm error code ENOTEMPTY npm error syscall rename npm error path /Users/userName/.npm/_npx/0496d3f111c50e47/node_modules/@modelcontextprotocol/sdk npm error dest /Users/userName/.npm/_npx/0496d3f111c50e47/node_modules/@modelcontextprotocol/.sdk-SXsa55pC npm error errno -66 npm error ENOTEMPTY: directory not empty, rename '/Users/userName/.npm/_npx/0496d3f111c50e47/node_modules/@modelcontextprotocol/sdk' -> '/Users/userName/.npm/_npx/0496d3f111c50e47/node_modules/@modelcontextprotocol/.sdk-SXsa55pC' npm error A complete log of this run can be found in: /Users/userName/.npm/_logs/2025-07-10T14_58_43_527Z-debug-0.log

[byPawel]

did update to. v1.0.44, and all my 11 mcps stopped working instantly, even the custom ones, also claude code started crashing on "escape" but i can see there are other issues mentioning this

e're investigating a potential fix. Some questions:

• Is this strictly happening to people with multiple MCP servers? How many do you have?
• Are the servers configured as npx commands or as local node/docker commands? Or a mix? It sounds like it's both, but want to make sure.

Had to reinstall all MCPs after they crashed following a recent update. My ~/.claude.json also got corrupted (ballooned to 3MB+ from paste history).

Here's my current MCP setup after rebuilding everything:

🌍 Global User Level (~/Library/Application Support/Claude/claude_desktop_config.json):

• MCP_DOCKER: docker mcp gateway run - i've installed it after all MCPs crashed after update.

📁 Project Level (.mcp.json):

• devlog-core: node ./mcp-devlog/bin/devlog-core.js
• devlog-search: node ./mcp-devlog/bin/devlog-search.js
• devlog-analytics: node ./mcp-devlog/bin/devlog-analytics.js
• devlog-planning: node ./mcp-devlog/bin/devlog-planning.js
• chromadb-devlog: python3 ./mcp-servers/chromadb/server.py
• elevenlabs-mcp: npx elevenlabs-mcp

💻 Local/Session Level (.claude-code-mcp.json + claude mcp list):

• playwright-mcp: node ~/work/playwright-mcp/dist/index.js
• devlog-core: node ./mcp-devlog/bin/devlog-core.js
• devlog-search: node ./mcp-devlog/bin/devlog-search.js
• devlog-analytics: node ./mcp-devlog/bin/devlog-analytics.js
• devlog-planning: node ./mcp-devlog/bin/devlog-planning.js
• chromadb-devlog: python3 ~/project/mcp-servers/chromadb/server.py
• devlog-mcp: node ~/project/mcp-devlog/dist/cjs/server.js (custom MCP with ChromaDB integration)
• notion-mcp: node ~/project/mcp-servers/notion-custom/server.js
• think-mcp-server: ~/project/mcp-servers/think-mcp-server/start.sh
• telegram-notifier: node ~/project/mcp-servers/telegram/server-enhanced.js
• playwright: http://localhost:9002/mcp (HTTP)

📝 Additional Local Config (.claude-code-mcp.json):

• mcp-atlassian-sse: http://localhost:9000/sse
• nx-mcp: npx nx-mcp
• devlog: node mcp-devlog/dist/cjs/server.js - specific projects - specific stuff
• think-mcp: node mcp-servers/think-mcp-server/dist/server.js
• perplexity-researcher: [pending reinstall]
• perplexity-ask: [pending reinstall]

Note: devlog is my custom MCP with ChromaDB vector search included. Some MCPs are running through Docker containers.

[MaxwellEdisons]

When I use the same .mcp.json file in ubuntu claude code works fine. However, in WSL under Windows, Ubuntu prompts that it cannot be connected

[pjgoodall]

We're investigating a potential fix. Some questions:

• Is this strictly happening to people with multiple MCP servers? How many do you have?
• Are the servers configured as npx commands or as local node/docker commands? Or a mix? It sounds like it's both, but want to make sure.

Just my local gitea server, which Gemini connected to immediately. https://gitea.com/gitea/gitea-mcp