{
  "markdown": "# @kakunin/mcp — MCP server for AI agent identity & compliance\n\n[![OpenSSF Scorecard](https://api.securityscorecards.dev/projects/github.com/kakunin-ai/kakunin-mcp/badge)](https://scorecard.dev/viewer/?uri=github.com/kakunin-ai/kakunin-mcp)\n[![kakunin-mcp MCP server](https://glama.ai/mcp/servers/nqzai/kakunin-mcp/badges/score.svg)](https://glama.ai/mcp/servers/nqzai/kakunin-mcp)\n\n<a href=\"https://glama.ai/mcp/servers/nqzai/kakunin-mcp\">\n  <img width=\"380\" height=\"200\" src=\"https://glama.ai/mcp/servers/nqzai/kakunin-mcp/badges/card.svg\" alt=\"kakunin-mcp MCP server\" />\n</a>\n\nModel Context Protocol server for the [Kakunin](https://kakunin.ai) AI agent compliance API. Lets AI agents self-verify scope, check their own risk score, and log behavioral events — all from within Claude, Cursor, or any MCP-compatible runtime.\n\n```bash\nnpx @kakunin/mcp\n```\n\n## Tools\n\n### `verify_agent_scope`\nCheck whether this agent is authorised to perform an action before executing it. Verifies the active X.509 certificate, permitted_actions scope, financial limits, and revocation status.\n\n```json\n{\n  \"action\": \"initiate EUR/USD trade on euronext for 50000 USD\",\n  \"venue\": \"euronext\",\n  \"amount_usd\": 50000\n}\n```\n\nReturns `{ allowed: true|false, reason, certificate_status, permitted_actions }`.\n\n### `check_risk_score`\nRetrieve the agent's rolling 30-day risk score, band (`low`/`medium`/`high`), drift trend, and actionable guidance. No input required.\n\n### `audit_log_append`\nAppend a behavioral event to the agent's immutable audit log. Returns risk score + transaction ID. Events scoring ≥ 0.85 auto-trigger a certificate revocation check.\n\n```json\n{\n  \"action_type\": \"transaction_initiated\",\n  \"details\": { \"amount_usd\": 50000, \"venue\": \"NYSE\" }\n}\n```\n\n## Setup\n\n**Prerequisites:** Node ≥ 18, Kakunin API key + Agent ID from [kakunin.ai/dashboard](https://kakunin.ai/dashboard).\n\n### Claude Desktop\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"kakunin\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@kakunin/mcp\"],\n      \"env\": {\n        \"KAKUNIN_API_KEY\": \"kak_live_...\",\n        \"KAKUNIN_AGENT_ID\": \"agt_...\"\n      }\n    }\n  }\n}\n```\n\n### Environment variables\n\n| Variable | Required | Description |\n|---|---|---|\n| `KAKUNIN_API_KEY` | ✅ | API key (`kak_live_...` or `kak_test_...`) |\n| `KAKUNIN_AGENT_ID` | ✅ | Agent ID the server acts on behalf of |\n| `KAKUNIN_BASE_URL` | optional | Override API base (default: `https://kakunin.ai`) |\n\n## Sandbox mode\n\nUse a `kak_test_...` key for development — hits the sandbox CA, no cost, 100 free certs/day.\n\nFull docs at [docs.kakunin.ai](https://docs.kakunin.ai).\n\n## Contributors\n\n<!-- ALL-CONTRIBUTORS-BADGE:START - Do not remove or modify this section -->\n<!-- ALL-CONTRIBUTORS-BADGE:END -->\n\nThanks to everyone who contributes ([emoji key](https://allcontributors.org/docs/en/emoji-key)) — code and non-code alike:\n\n<!-- ALL-CONTRIBUTORS-LIST:START - Do not remove or modify this section -->\n<!-- prettier-ignore-start -->\n<!-- markdownlint-disable -->\n<!-- markdownlint-restore -->\n<!-- prettier-ignore-end -->\n<!-- ALL-CONTRIBUTORS-LIST:END -->\n\nContributions of any kind are welcome — this project follows the [all-contributors](https://allcontributors.org) spec.\n",
  "bytes": 3279,
  "sha": "1d8f15f12e9a719fb294bbd52b958a5fb34dfc838e57a7c9dd95dcf6bf69db62",
  "repo_slug": "kakunin-ai/kakunin-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_kakunin_ai_kakunin_c6743136/readme"
}