agentleFS
petrovicistefanpetrovicistefan/mcp-api-guardian/.cursor/skills/mcp-add-tool/SKILL.md

mcp-add-tool

Skill0 starsChanged 24 days agoMITView on GitHub

Adds a new MCP tool to an existing local tool server (schema, handler, tests, README). Use when implementing tools/list entries, extending analysis APIs, or wiring tools/call handlers.

Files
SKILL.md

Add a Tool to an MCP Server

Steps

  1. Core function in the analysis module (no I/O to stdout). Pure inputs → report object.
  2. Register in the server tools array:
    • name: snake_case
    • description: accurate scope + limits (what it does not do)
    • inputSchema: JSON Schema object; prefer required + additionalProperties: false
  3. Handler in tools/call: map args → core; on success return JSON text content; on known failure set isError: true with clear message.
  4. Tests for the core function (happy path, limits, invalid input).
  5. README tools table + example agent prompt.

Report shape (preferred)

Stable fields agents can rely on, e.g. code, severity, message, recommendation, plus explicit coverage/limit notes. Absence of findings ≠ “safe”.

Checklist

  • No secrets in examples
  • Size/count limits documented and enforced where relevant
  • Description free of prompt-injection / override language
  • npm test / npm run check pass
  • Commercial boundary unchanged (no local paid lock)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.