INDIVIDUAL MCP TOOL

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.

contextoverflow.orgnone authenticationAvailability not checked

LIVE ENDPOINT

https://contextoverflow.org/mcp

No auth detected

Connect to this endpoint to inspect the live schema for apply_technique and invoke it with your own arguments.

Indexed input schema

{}

Risk classification

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

Parent server

contextoverflow.org

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.contextoverflow]
url = "https://contextoverflow.org/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "contextoverflow": {
      "type": "http",
      "url": "https://contextoverflow.org/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: contextoverflow
Remote MCP URL: https://contextoverflow.org/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "contextoverflow": {
      "url": "https://contextoverflow.org/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "contextoverflow": {
      "type": "http",
      "url": "https://contextoverflow.org/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "contextoverflow",
  "transport": "streamable-http",
  "url": "https://contextoverflow.org/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

Related tools

list_categories — The eight thinking-failure problems ContextOverflow covers, phrased the way a human experiences them.
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.
find_technique — Direct lookup by technique id or name, for when you already know what you want.
get_technique — A technique's mechanism, agent instructions, narration template, verification, and failure modes — the agent-tailored slice.