{
  "markdown": "# Compliance MCP Skill Example\n\n[![smithery badge](https://smithery.ai/badge/theartofservice/compliance-intelligence)](https://smithery.ai/servers/theartofservice/compliance-intelligence)\n\nA minimal, working example of an AI agent skill that uses the [TheArtOfService Compliance MCP](https://api.theartofservice.com/mcp) as its source-grounded knowledge layer.\n\nThe hosted server is listed on [Smithery](https://smithery.ai/servers/theartofservice/compliance-intelligence) and in the [official MCP registry](https://registry.modelcontextprotocol.io/v0/servers?search=theartofservice) as `com.theartofservice/compliance-intelligence`. Endpoint: `https://api.theartofservice.com/mcp` (streamable HTTP, anonymous access).\n\nTwo working examples: one for compliance research, one for the course catalogue. This is a **reference implementation**. Clone it, swap the framework name to whatever your agent needs, plug it into Claude / GPT / Copilot / your own agent runtime. Apache 2.0 licensed, no strings attached.\n\n## What this does\n\nGiven a compliance framework name (default: `NIST SP 800-161`), this script:\n\n1. Connects to the compliance API at `https://api.theartofservice.com`\n2. Pulls the framework metadata\n3. Pulls all controls in the framework\n4. For each control, fetches the auditor evidence requirements (categories, artefacts, common gaps, source citations)\n5. Generates a structured Markdown compliance brief\n\nThe output is suitable for piping into an LLM as context, or directly handing to an auditor or risk team.\n\n## Why this pattern works\n\nThe compliance corpus behind the API is **source-grounded against the published standard text** and **human edited**, not LLM-generated. That makes it the authoritative knowledge layer for any agent that needs to reason about compliance controls.\n\nYour agent provides the **tribal knowledge** layer (the organization's specific context, the tone, the workflow). The platform provides the **official knowledge** layer. The split is what makes the resulting brief defensible.\n\n## Stats\n\n- 723 compliance frameworks\n- 20,400+ controls\n- 332,000+ cross-framework mappings\n- 314,000+ courses in the catalogue, searchable without a key\n- 28,586+ controls carry structured auditor evidence requirements\n- Source-grounded, version-tagged, refreshed weekly\n\n## Quickstart\n\n```bash\ngit clone https://github.com/GJB65/compliance-mcp-skill-example.git\ncd compliance-mcp-skill-example\npip install -r requirements.txt\ncp .env.example .env\n# Edit .env and add your TAOS_API_KEY from https://compliance.theartofservice.com/settings\npython run.py \"NIST SP 800-161\"\n```\n\nThe script will print a Markdown brief to stdout. Redirect it to a file or pipe it into your downstream agent.\n\n```bash\npython run.py \"ISO 27001:2022\" > iso_27001_brief.md\n```\n\n## Second example: the course catalogue\n\n`run.py` answers *what does this framework require*. `find_courses.py` answers the other\nhalf: *what can the user actually do about it*.\n\n```bash\npython find_courses.py \"soc 2 evidence collection\"\npython find_courses.py \"first 90 days as CISO\" --framework \"ISO 27001\"\npython find_courses.py --overlap \"SOC 2,ISO 27001\"\npython find_courses.py --frameworks\n```\n\n**No API key needed.** The four catalogue tools are free and unmetered, because they exist\nto help a buyer find the right course rather than to meter access to data.\n\nThe interesting one is `--overlap`. A plain product listing cannot answer \"we are running\nSOC 2 and ISO 27001 at the same time, what covers both\", because that is a join, not a\nsearch. An organisation in that position does not want one course per standard, it wants\nthe overlap:\n\n```\n# Courses covering SOC 2,ISO 27001 together\n\n### SOC 2 Type 2 Security controls in ISO 27001\n- Price: $299.00 USD\n- Covers: ISO 27001, SOC 2\n- Buy: https://store.theartofservice.com/...\n```\n\nWhen nothing covers the whole combination, it says so and reports what exists per standard\nrather than returning an empty list.\n\nLink buyers to the `buy_url` field. It carries attribution, which is how the catalogue\nknows an agent produced the sale.\n\n## Get an API key\n\n1. Sign up free at [compliance.theartofservice.com/register](https://compliance.theartofservice.com/register).\n2. Your API key (prefix `tas_`) is in your account settings.\n3. Free tier: 100 calls/month. Professional ($49/mo): 10,000 calls/month plus overage at $0.005/call.\n4. For data licensing, white-label, or volume pricing, see the [developer portal](https://compliance.theartofservice.com/developers).\n\n## Using as a Claude skill\n\nThe `SKILL.md` file in this repo is structured as a Claude skill definition. Drop the repo into your Claude Code or Claude Desktop skills folder and Claude can invoke `run.py` directly with a framework name.\n\n## API endpoints used\n\nThis example hits the public REST agent API. The same data is available via the MCP endpoint at `https://api.theartofservice.com/mcp` if you prefer Model Context Protocol over REST.\n\n| Endpoint | Used for |\n|---|---|\n| `GET /api/agent/frameworks/{name}` | Framework metadata |\n| `GET /api/agent/frameworks/{name}/controls` | All controls in the framework |\n| `GET /api/agent/controls/{code}` | Full control detail including evidence_requirements |\n| `GET /api/agent/courses` | Search the course catalogue (free, no key) |\n| `GET /api/agent/courses-for-frameworks` | Courses covering two or more standards together |\n| `GET /api/agent/courses/{product_id}` | Full detail for one course |\n| `GET /api/agent/course-frameworks` | Standards covered, with course counts |\n\nFull tool catalog: [compliance.theartofservice.com/developers](https://compliance.theartofservice.com/developers)\n\n## License\n\nApache 2.0. See `LICENSE`.\n\n## Contributions\n\nIssues and PRs welcome. If you build a derivative skill (vendor risk, SOC 2 audit prep, framework-specific advisor, etc.) and want it linked from the example registry, open a PR with a one-line description and a repo URL.\n",
  "bytes": 5928,
  "sha": "6f36bb26018e0edd30ca3685782858d2de22fbf18847b9957413c65618ce373a",
  "repo_slug": "gjb65/compliance-mcp-skill-example",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_com_theartofservice_compliance_intellige_06ef3708/readme"
}