Notes from a 2 AM On-Call: Why Our Stitch MCP Server Died Silently on Tool Timeouts
At 2:14 AM PST, our Stitch MCP server process ( stitch-skills ) running against Claude Code agents went dark. No crash logs. No stderr output. Just a silent exit 0 and a socket EOF on the client side.
The raw symptom:
[ claude-code ] Error: MCP server connection lost ( code: 0 ) [ stitch-skills ] ( no output, clean exit ) [ docker stats ] stitch-skills container: 137 ( OOMKilled? No. )
Enter fullscreen mode
Exit fullscreen mode
No OOM. No segfault. Just a graceful suicide.
The Red Herring
Every MCP tutorial tells you to wrap tool handlers in try-catch. We did:
// What the docs recommend server . setRequestHandler ( CallToolRequestSchema , async ( request ) => { try { const result = await executeSkill ( request . params . name , request . params . arguments ) ; return { content : [ { type : "text" , text : JSON .…