agentleFS
petrovicistefanpetrovicistefan/mcp-api-guardian/.cursor/skills/mcp-control-plane-integrate/SKILL.md

mcp-control-plane-integrate

Skill0 starsChanged 24 days agoMITView on GitHub

Integrates a hosted or trusted service with MCP control-plane auth, entitlements, and usage consume. Use when wiring quotas, API keys, billable operations, or adding a product ID to the control plane.

Files
SKILL.md

Integrate with Control Plane

Prerequisites

  • Control plane running (ADMIN_TOKEN ≥32 chars, SQLite path, bind 127.0.0.1 locally)
  • Product ID already in products in src/store.js (or add it + tests + README in the same change)

Note: mcp-security-guard paid Team/threat-feed today uses mcp-security-cloud (cloud.ts / team.ts), not this consume API. Use this skill for family-wide quota backends or a deliberate future unification — do not redirect security-guard cloud traffic here by accident.

Admin bootstrap

POST /v1/admin/accounts
Authorization: Bearer <ADMIN_TOKEN>
{ "accountId": "customer-1" }

POST /v1/admin/keys
{ "accountId": "customer-1" }
→ { "key": "mcp_…", "keyId": "<sha256>" }   # raw key shown once

PUT /v1/admin/plan
{ "accountId": "customer-1", "plan": "paid" }  # admin only — not payment proof

Customer billable path

GET /v1/entitlements
Authorization: Bearer mcp_…

POST /v1/usage/consume
{ "product": "api-guardian", "requestId": "scan-123", "units": 1 }
StatusMeaningAction
200allowed (or duplicate same units)Proceed
429over quotaDo not run billable work
409requestId reused with different unitsNew requestId or fix units
401bad/revoked keyFail closed

Checklist when adding a product ID

  • Append ID to products in store.js
  • Extend tests for consume/entitlements
  • Update control-plane README product list
  • Document consume call site in the hosted service (not in bypassable local MVP unless hosted)

Do not

  • Send report bodies, source, or DB credentials to control-plane
  • Implement refunds/Stripe in ad-hoc form without webhook verification
  • Share SQLite over NFS or expose admin routes publicly

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.