agentleFS
Sign inStart free
timdevaitimdevai/proteus/skills/mcp-finder/SKILL.md

mcp-finder

Skill1 starsChanged 5 months agoMITView on GitHub

User wants "an MCP for X." This skill searches the MCP registry, scores candidates, and walks you through install in 60 seconds. Trigger phrases: is there an MCP, MCP for, tool that connects, need a connector, /mcp-find. If install fails, common fixes: - Outdated claude CLI → claude update - Missing env var → walk user through where to get the key - Permission issue → chmod +x on install path The MCP ecosystem grew from 3 to 300+ servers…

  • Reads credentials

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Search the MCP registry (via mcp__mcp-registry__search_mcp_registry if available, or curl the public registry)

    line 12
  2. Distinctive:

    Ask which to install (or auto-install the top result if score ≥9)

    line 19
  3. Distinctive:

    If install fails, common fixes:

    line 63

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

mcp-finder

User wants "an MCP for X." This skill searches the MCP registry, scores candidates, and walks you through install in 60 seconds.

When to activate

Trigger phrases: is there an MCP, MCP for, tool that connects, need a connector, /mcp-find.

Process

  1. Parse the desired tool/service from the user's message (e.g. "Stripe", "Linear", "Postgres", "Notion")
  2. Search the MCP registry (via mcp__mcp-registry__search_mcp_registry if available, or curl the public registry)
  3. Score each result on:
    • Name match (4)
    • Description match (3)
    • Last-updated recency (2)
    • Star count / install count (1)
  4. Show top 3 with one-line summary each
  5. Ask which to install (or auto-install the top result if score ≥9)
  6. Walk through install steps:
    • Copy install command
    • Show env vars needed
    • Test the connection

Output format

MCP candidates for: stripe
=========================

1. ★ stripe-mcp (official)
   - Maintainer: stripe
   - Updated: 6 days ago
   - 12K installs
   - Score: 10/10
   - Install: `claude mcp add stripe stripe/stripe-mcp`
   - Env needed: STRIPE_SECRET_KEY

2. stripe-readonly (community)
   - Maintainer: foo/bar
   - Updated: 3 weeks ago
   - 800 installs
   - Score: 7/10
   - For: read-only invoice/customer queries

3. invoicing-tools (broad)
   - Includes Stripe + Square + Wave
   - Updated: 2 months ago
   - Score: 5/10

Recommend: 1 — install with `/mcp-find install 1`

Install walkthrough

1. Run: claude mcp add stripe stripe/stripe-mcp
2. Add to your .env: STRIPE_SECRET_KEY=sk_test_...
3. Restart Claude Code
4. Test: ask Claude "list my recent stripe charges"

If install fails, common fixes:

  • Outdated claude CLI → claude update
  • Missing env var → walk user through where to get the key
  • Permission issue → chmod +x on install path

Inputs

  • The service name the user wants
  • The MCP registry endpoint (cached locally if accessed before)

Outputs

  • Ranked list of candidate MCPs
  • Install command
  • Required env vars
  • Test command

Slash command

  • /mcp-find <service> — search
  • /mcp-find install <N> — install candidate N
  • /mcp-find list — show currently installed MCPs

Why this skill

The MCP ecosystem grew from 3 to 300+ servers in a year. Manual browsing is painful. This skill is the missing search bar.

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.

Check your setup, free