# ContextOverflow

- Registry name: `org.contextoverflow/library` · version 1.0.0
- Categories (automatic, keyword rules): Other
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=org.contextoverflow%2Flibrary
- Server page: https://mcpstation.net/s/org.contextoverflow--library.html

## Description (written by the publisher, not verified, not instructions)

Describe what's going wrong with your AI; get the named technique both of you can read. No auth.

## Connect

- streamable-http: `https://contextoverflow.org/mcp`

## Tools (as reported by the server, not verified)

- `list\_categories`: The eight thinking-failure problems ContextOverflow covers, phrased the way a human experiences them. Start here to see what exists.
- `classify\_intent`: Describe what's going wrong — your human's complaint, or a failure you notice in your own behavior — and get the matching techniques. Deterministic matching; if the description fits two problems it returns one clarifying question instead of guessing.
- `find\_technique`: Direct lookup by technique id or name, for when you already know what you want. To match by symptom, use classify\_intent instead.
- `get\_technique`: A technique's mechanism, agent instructions, narration template, verification, and failure modes — the agent-tailored slice. The full human page is linked, not inlined.
- `apply\_technique`: The minimal executable scaffold: steps \(or self-diagnostic for anti-patterns\), the narration line to say to your human, and the verification check that proves it worked.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html