Skip to content

ContextOverflow

by contextoverflow.org · remote · no sign-in to list tools · v1.0.0 · published by org.contextoverflow

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

Changes · 1

5 tools: 1 change things and 4 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http library https://contextoverflow.org/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

5 tools

Changes things 1Claude Code: ask
  • apply_techniqueThe 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.No findings

    Why it is in this group

    • The name "apply_technique" says "apply": a word for a change.
    Description, as the server wrote it
    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.
Only reads 4Claude Code: allow
  • classify_intentDescribe what's going wrong — your human's complaint, or a failure you notice in your own behavior — and get the matching techniques.No findings

    Why it is in this group

    • The description's first verb is "describe": a word for reading.
    Description, as the server wrote it
    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_techniqueDirect lookup by technique id or name, for when you already know what you want.No findings

    Why it is in this group

    • The name "find_technique" says "find": a word for reading.
    Description, as the server wrote it
    Direct lookup by technique id or name, for when you already know what you want. To match by symptom, use classify_intent instead.
  • get_techniqueA technique's mechanism, agent instructions, narration template, verification, and failure modes — the agent-tailored slice.No findings

    Why it is in this group

    • The name "get_technique" says "get": a word for reading.
    Description, as the server wrote it
    A technique's mechanism, agent instructions, narration template, verification, and failure modes — the agent-tailored slice. The full human page is linked, not inlined.
  • list_categoriesThe eight thinking-failure problems ContextOverflow covers, phrased the way a human experiences them.No findings

    Why it is in this group

    • The name "list_categories" says "list": a word for reading.
    Description, as the server wrote it
    The eight thinking-failure problems ContextOverflow covers, phrased the way a human experiences them. Start here to see what exists.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http library https://contextoverflow.org/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__library__list_categories",
      "mcp__library__classify_intent",
      "mcp__library__find_technique",
      "mcp__library__get_technique"
    ],
    "ask": [
      "mcp__library__apply_technique"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as library. Review it before you use it.