Menu

1 / 5

Notes from a 2 AM On-Call: Why Our Stitch MCP Server Died Silently on Tool Timeouts

DEV Community: typescript·Lucas Vance·41 minutes ago
#FKPwiolo
#devtotypescript#devto#dev#transport#stitch
Reading 0:00
15s threshold

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 .…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.