{
  "markdown": "# Kanonik\n\nGovernance runtime for compliance work, connected to Grok over MCP.\n\nKanonik gives your AI a typed compliance model to work in, a tamper-evident\nrecord of everything it does, a server-side Verifier that checks its work, and a\nhuman-approval gate in front of every write. Your AI does the reasoning. Kanonik\nmakes the result defensible.\n\n## What you can do with it\n\nAsk your AI to work on your compliance program in plain language:\n\n- Draft and revise policies and procedures against a loaded framework\n- Assess internal controls and record the evidence behind each judgement\n- Find the gaps between what a framework requires and what you actually have\n- Build an audit trail an assessor can verify independently\n- Produce a Statement of Applicability, or the equivalent artifact for your framework\n\nThe framework in scope comes from your workspace. Kanonik runs ISO 27001:2022,\nSOC 2, GDPR, NIST CSF 2.0 and HIPAA today. Nothing in the plugin is specific to\nany one of them.\n\n## Installing\n\n```\n/marketplace\n```\n\nThen pick Kanonik. Or from the CLI:\n\n```\ngrok plugin install kanonik --trust\n```\n\nOn first use your AI connects to `https://app.kanonik.ai/mcp` and a browser\nwindow opens for sign-in. You will need a Kanonik account; sign up at\n[kanonik.ai](https://kanonik.ai).\n\n## What this plugin contains\n\nOne file that tells Grok where the Kanonik MCP server lives:\n\n```json\n{\n  \"mcpServers\": {\n    \"kanonik\": { \"type\": \"http\", \"url\": \"https://app.kanonik.ai/mcp\" }\n  }\n}\n```\n\nThat is the whole plugin. There is no bundled code, no install script, no hook,\nand no local process. Everything runs server-side at Kanonik.\n\n## Permissions and data\n\n- **Network.** One endpoint, `https://app.kanonik.ai/mcp`. Nothing else.\n- **Authentication.** OAuth 2.1 with Dynamic Client Registration and PKCE,\n  against `https://auth.kanonik.ai`. Tokens are held by your Grok client. The\n  plugin holds no credential and ships no secret.\n- **Scopes.** `kanonik:read` to read your compliance record, `kanonik:propose`\n  to draft changes, `kanonik:commit` to submit them for approval.\n- **Writes.** No change reaches your record without a signed single-use approval\n  token and a human clicking to approve it. Your AI cannot approve its own work.\n- **Your other systems.** Kanonik never holds credentials to your source systems.\n  If your AI reads from GitHub, Jira, or your identity provider, it does so\n  through its own connections, not through Kanonik.\n\n## Links\n\n- Site: [kanonik.ai](https://kanonik.ai)\n- Documentation: [kanonik.ai/docs](https://kanonik.ai/docs/)\n- Contact: [kanonik.ai/contact](https://kanonik.ai/contact)\n\n## License\n\nSee [LICENSE](LICENSE). The Kanonik service itself is proprietary; this\nrepository contains only the connection manifest and documentation for it.\n",
  "bytes": 2783,
  "sha": "d7dc07e1b144db939c46781c2050da6da2ea5ea331384d2313fcbcbcca6d91fc",
  "repo_slug": "kanonik-llc/kanonik-plugin",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_kanonik_kanonik_863cf8e4/readme"
}