mcp-api-guardian / rules
Cursor rule0 starsChanged 24 days agoMITView on GitHub
MCP product family architecture, commercial boundary, and shared conventions
- Reads credentials
We split this mcp-family.mdc into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
No telemetry. Network only on explicit opt-in (supply-chain, threat feed, Team, live probes).
- Distinctive: line 26
Never send paths, args, env, headers, tool bodies, file content, or secrets in cloud payloads.
- Very specific: line 31
Prefer matching the sibling’s existing stack (security-guard: TS + SDK + vitest.
- Very specific: line 32
Do not claim npx / Registry listing until actually published (security-guard already is).
≈ “Common” is an estimate: at least 1 in 5 of the 6,350 Cursor rule 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.
Files
--- description: MCP product family architecture, commercial boundary, and shared conventions alwaysApply: true --- # MCP Family | Piece | Role | Maturity | | --- | --- | --- | | `mcp-control-plane` | Shared HTTP accounts/keys/quotas API (not an MCP server) | MVP | | `mcp-security-guard` | Audit MCP servers / agent context; Claude plugin + CLI + Action | **Shipped ~0.8.x** — reference product | | Other tool products | Local-first analysis MCP servers | Early MVP (~0.1.0) | Control-plane product IDs: `security-guard`, `dependency-doctor`, `api-guardian`, `database-doctor`, `cost-optimizer`, `seo-auditor`. ## Commercial boundary - Local MIT tools stay fully useful **without** a key. Never add bypassable local counters as paid enforcement. - **security-guard paid path today:** opt-in `MCP_SECURITY_API_KEY` → `mcp-security-cloud` (threat feed + Team). Keys issued by hand / Lemon Squeezy; free plugin unchanged. - **Family-wide quotas (control-plane):** for trusted hosted billable ops via `/v1/usage/consume`. Do not conflate with security-guard’s cloud unless deliberately unifying later. - Admin-set control-plane `paid` ≠ payment proof. Document README prices as hypotheses until live. ## Privacy defaults - No telemetry. Network only on explicit opt-in (supply-chain, threat feed, Team, live probes). - Never send paths, args, env, headers, tool bodies, file content, or secrets in cloud payloads. - Findings are review prompts; state coverage limits. ## Engineering - Prefer matching the **sibling’s existing stack** (security-guard: TS + SDK + vitest; many MVPs: zero-dep Node ESM + `node:test`). - Do not claim `npx` / Registry listing until actually published (security-guard already is). - Protocol claims must match code; no fake “complete validator” wording.
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 3,978 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository6 other files it gives its agents.
- .cursor/rules/mcp-privacy-security.mdcCursor rule
- .cursor/rules/mcp-tool-server.mdcCursor rule
- mcp-add-toolSkill
- mcp-control-plane-integrateSkill
- mcp-family-architectureSkill
- mcp-ship-checklistSkill
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
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.