Regulated Ai Compliance
mcp-regulated-ai-compliance
A Model Context Protocol server exposing the regulated-industry AI compliance knowledge from hellouchit.com as tools, resources, and prompts callable from any MCP-compatible AI client — Claude Desktop, Cursor, Zed, Windsurf, OpenAI ChatGPT, Continue, Cline, and ~40 other clients.
Free + open-source (Apache 2.0, dataset CC BY 4.0). Built by Uchit Vyas.
Disclaimer: This is a personal, open-source, non-commercial project. Views are my own. It is not affiliated with, endorsed by, or representative of my employer.
Why this exists
The OpenAI GPT Store hosts the EU AI Act and AU AI Safety Standard coaches as ChatGPT-only assets. The Claude Project equivalents are private to each user's Claude Pro account (no public sharing). Neither reaches the practitioners who work primarily inside Cursor, Zed, Continue, Cline, or the Claude API directly.
An MCP server is the only Claude-side asset that is genuinely shareable + multi-client. It surfaces the same dataset, anti-patterns, decision trees, and classification logic — but as tools any AI agent in any compatible client can call. One published server → 40+ client surfaces → the practitioner who never opens ChatGPT or claude.ai still ends up citing your work.
What's in this folder
mcp-regulated-ai-compliance/
├── README.md ← you are here
├── scope/ ← the design docs (read FIRST)
│ ├── 00-product-brief.md What this is + who it's for
│ ├── 01-architecture.md System design + transport choices
│ ├── 02-tools-spec.md The 10 tools the server exposes
│ ├── 03-resources-spec.md The resources + prompts
│ ├── 04-distribution-strategy.md Where to list + how to get installs
│ └── 05-build-roadmap.md v0.1 → v1.0 in 4 phases
├── src/
│ ├── index.ts ← MCP server entry point (working stub)
│ ├── tools/ ← one file per tool
│ │ └── lookup-control.ts ← FULLY IMPLEMENTED as reference
│ ├── resources/ ← one file per resource type
│ ├── prompts/ ← pre-built prompt templates
│ ├── data/ ← embedded knowledge (dataset, anti-patterns, playbooks)
│ │ ├── dataset.json ← 56 controls × 28 regulations × 261 tools
│ │ ├── dataset.csv ← same data, CSV format
│ │ ├── anti-patterns.md ← 15 named failure modes
│ │ └── playbooks/ ← 90-day playbooks
│ └── lib/
├── docs/
│ └── install/ ← per-client install guides
├── examples/ ← sample conversations / use-cases
├── tests/
├── package.json ← npm config (working)
├── tsconfig.json ← TypeScript config
├── LICENSE ← Apache 2.0 (code) + CC BY 4.0 (dataset)
├── .gitignore
└── .github/workflows/ ← CI: build + publish to npm
Status — v0.2.1 shipped 2026-05-29
v0.2.1 = data-source abstraction so the same codebase runs on Node (stdio, node:http) AND on Cloudflare Workers / Deno Deploy / Vercel Edge. See
worker/for the Cloudflare scaffold.
| Phase | Status |
|---|---|
| Phase 0 — Scope + skeleton | ✅ done |
| Phase 1 — Working server + reference tool | ✅ done |
| Phase 2 — 6 core tools | ✅ done |
| Phase 3 — 4 resource providers + 5 prompts | ✅ done |
| Phase 4 — npm publish + directory submissions | ✅ done |
| Phase 5 — HTTP transport + 4 playbooks + parser | ✅ done (v0.2.0) |
v0.2.0 ships with
- Streamable HTTP transport —
npx mcp-regulated-ai-compliance-httpboots a Node HTTP server on port 3000 (configurable) at/mcp. Unlocks Smithery, ChatGPT MCP directory, browser-based clients, and any platform that prefers HTTP over stdio. Stateless by default; setMCP_STATEFUL=truefor per-session UUIDs. - All 4 playbooks fully structured — markdown parser extracts 12-week / 12-gate / phase / anti-pattern / source-URL data:
eu-ai-act-12-weeks— Piloting → Articles 9-15 ready by 2 Aug 2026cisa-attestation-90-days— Federal contractor SSDF + Common Form 3201-NEWcloud-cost-aware-to-controlled— FinOps Aware → Controlled (AWS / Azure / GCP)vault-theatre-to-workload-identity— Long-lived creds → OIDC federation
- 6 tools —
lookup_control·get_anti_pattern·crosswalk·walk_playbook·classify_use_case·list_regulations - 4 resource providers (56 URIs) — full dataset (+ by-regulation + by-category), 15 anti-patterns (bundled + per-slug), 4 playbooks, the 20-entry crosswalk matrix
- 5 prompts —
eu-ai-act-classify·au-ai-safety-walkthrough·crosswalk-frameworks·playbook-week·anti-pattern-diagnostic - Embedded knowledge — 56 controls × 28 regulations × 261 tools, 15 named anti-patterns, 4 × 12-week playbooks, 20 crosswalks
- CI + tests — GitHub Actions on Node 22 + 24, 24/24 unit tests, automated
npm publish --provenanceon version tag (sigstore-anchored)
Where you can find it
| Channel | Status |
|---|---|
| npm | ✅ @hellouchit/mcp-regulated-ai-compliance@0.2.0 |
| Official MCP Registry | ✅ io.github.uchit/mcp-regulated-ai-compliance@0.2.1 (latest) |
| Glama | ✅ verified |
| mcp.so | ⏳ awaiting review |
| PulseMCP | ⏳ auto-pulls from Official Registry (~24h) |
| awesome-mcp-servers (Security) | ⏳ PR #7084 |
| Hosted endpoint | ✅ https://mcp.hellouchit.com/mcp (Cloudflare Worker · stateless) |
| Smithery | ✅ smithery.ai/server/@uchit86/regulated-ai-compliance |
See scope/05-build-roadmap.md for the v0.2+ roadmap.
Quick install
For Claude Desktop:
# In your Claude Desktop config file (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"regulated-ai-compliance": {
"command": "npx",
"args": ["-y", "@hellouchit/mcp-regulated-ai-compliance"]
}
}
}
Then restart Claude Desktop → you'll see new tools available: lookup_control, classify_use_case, get_anti_pattern, etc.
Regulation slugs (use these exact values in tool arguments)
eu_ai_act · cps234 · cps230 · soci · ai_safety_au · privacy_au · e8 · irap · dora · nis2 · gdpr · circia · hipaa · fda_samd · cisa_ssa · ssdf · ai_rmf · sp80053 · iso42001 · iso27001 · slsa · owasp_llm · atlas · bcbs239 · pci · iec62443 · iso13485 · iec62304
Local development
npm install
npm run build
npm run dev # runs server in dev mode (stdio transport)
npm test # runs the test suite
See scope/01-architecture.md for the dev-loop details.
License
Code: Apache 2.0. Patent grant included. Dataset (regulations × controls × tooling, anti-patterns, playbooks, crosswalks): CC BY 4.0 — attribution to hellouchit.com required.
This is a personal, non-commercial project shared for the community. Contributions and issues are welcome on GitHub.
Server Config
{
"mcpServers": {
"regulated-ai-compliance": {
"command": "npx",
"args": [
"-y",
"@hellouchit/mcp-regulated-ai-compliance"
]
}
}
}