{"_id":"@akr1166org/rules-mcp","_rev":"2-7a45e253636b0e295c92c95040ea4451","name":"@akr1166org/rules-mcp","dist-tags":{"latest":"0.3.1"},"versions":{"0.3.0":{"name":"@akr1166org/rules-mcp","version":"0.3.0","keywords":["mcp","rules","ai-governance","cursor","claude","vscode","antigravity"],"license":"MIT","_id":"@akr1166org/rules-mcp@0.3.0","maintainers":[{"name":"akr1166org","email":"thumuruachyuth@gmail.com"}],"homepage":"https://github.com/AKR1166/Rules-MCP#readme","bugs":{"url":"https://github.com/AKR1166/Rules-MCP/issues"},"bin":{"rules-mcp":"dist/index.js"},"dist":{"shasum":"8ac5cfa6fd890bded7d5f1eb2eaa07ecc4b1da6e","tarball":"https://registry.npmjs.org/@akr1166org/rules-mcp/-/rules-mcp-0.3.0.tgz","fileCount":209,"integrity":"sha512-nu5VZfi39ItFzYeBP/w5TiWq4po+Ju85KofLk45sN5AtffULGlxfkR/ZUmNkyWWz87D674eczJyuy5fEFV3nFg==","signatures":[{"sig":"MEQCIHnfM5YeYq82SmrebLjJgqWxOryBCTxuJBnOG6Cs4nraAiB6Ng2ZWUdbTj2faa/qRdoBHuxvojkPn4cxHTMboMv7oA==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":940489},"main":"./dist/index.js","type":"module","types":"./dist/index.d.ts","engines":{"node":">=20"},"exports":{".":"./dist/index.js","./schema":"./dist/schema/rule.js"},"gitHead":"4e01bd8e06d75d4746166a27379cc0c1713119bd","mcpName":"io.github.AKR1166/rules-mcp","scripts":{"dev":"tsx src/index.ts","test":"tsx --test tests/**/*.test.ts","build":"tsc","serve":"node dist/index.js serve","start":"node dist/index.js","prepack":"npm run build","generate":"tsx src/index.ts generate","typecheck":"tsc --noEmit","test:watch":"tsx --test --watch tests/**/*.test.ts","link:global":"npm run build && npm link","unlink:global":"npm unlink -g rules-mcp","rules:validate":"tsx scripts/validate-rules.ts","validate:sample":"tsx src/index.ts validate \"const x: any = 1;\""},"_npmUser":{"name":"akr1166org","email":"thumuruachyuth@gmail.com"},"repository":{"url":"git+https://github.com/AKR1166/Rules-MCP.git","type":"git"},"_npmVersion":"11.8.0","description":"AI Governance MCP — structured skills, knowledge, and evaluation for Cursor, Claude, VS Code, and Antigravity","directories":{},"_nodeVersion":"24.13.1","dependencies":{"zod":"^4.4.3","yaml":"^2.9.0","@modelcontextprotocol/sdk":"^1.30.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.23.5","typescript":"^5.8.3","@types/node":"^26.1.2"},"_npmOperationalInternal":{"tmp":"tmp/rules-mcp_0.3.0_1786432029405_0.34645357127651377","host":"s3://npm-registry-packages-npm-production"}},"0.3.1":{"name":"@akr1166org/rules-mcp","version":"0.3.1","description":"AI Governance MCP — structured skills, knowledge, and evaluation for Cursor, Claude, VS Code, and Antigravity","mcpName":"io.github.AKR1166/rules-mcp","type":"module","bin":{"rules-mcp":"dist/index.js"},"main":"./dist/index.js","exports":{".":"./dist/index.js","./schema":"./dist/schema/rule.js"},"repository":{"type":"git","url":"git+https://github.com/AKR1166/Rules-MCP.git"},"bugs":{"url":"https://github.com/AKR1166/Rules-MCP/issues"},"homepage":"https://github.com/AKR1166/Rules-MCP#readme","scripts":{"build":"tsc","prepack":"npm run build","dev":"tsx src/index.ts","start":"node dist/index.js","serve":"node dist/index.js serve","link:global":"npm run build && npm link","unlink:global":"npm unlink -g rules-mcp","test":"tsx --test tests/**/*.test.ts","test:watch":"tsx --test --watch tests/**/*.test.ts","typecheck":"tsc --noEmit","rules:validate":"tsx scripts/validate-rules.ts","generate":"tsx src/index.ts generate","validate:sample":"tsx src/index.ts validate \"const x: any = 1;\""},"engines":{"node":">=20"},"keywords":["mcp","rules","ai-governance","cursor","claude","vscode","antigravity"],"license":"MIT","publishConfig":{"access":"public"},"dependencies":{"@modelcontextprotocol/sdk":"^1.30.0","yaml":"^2.9.0","zod":"^4.4.3"},"devDependencies":{"@types/node":"^26.1.2","tsx":"^4.23.5","typescript":"^5.8.3"},"gitHead":"750cfd8dfdd42e15ea8c5fb75e85a255b23f89f1","types":"./dist/index.d.ts","_id":"@akr1166org/rules-mcp@0.3.1","_nodeVersion":"24.13.1","_npmVersion":"11.8.0","dist":{"integrity":"sha512-l946Se7JsWgM4BMzDzYLA3HVjGdZniWI87oifMkdDjeeVd/xvlLHgdveFhFLIOHarUBU+Uo5l0UhBdHzjy0/SQ==","shasum":"ff1fa51c04fc9edbd0f6bd61fc8b75e4dd7c76f4","tarball":"https://registry.npmjs.org/@akr1166org/rules-mcp/-/rules-mcp-0.3.1.tgz","fileCount":209,"unpackedSize":940489,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEUCIEKDGYJw9QvPcTsCFRzoajnQ3dp53xziub2REW5YK68cAiEAl/JW9ow57spYms7c13/Cl0C7KG2iyMuj8aBpHuqWsfg="}]},"_npmUser":{"name":"akr1166org","email":"thumuruachyuth@gmail.com"},"directories":{},"maintainers":[{"name":"akr1166org","email":"thumuruachyuth@gmail.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/rules-mcp_0.3.1_1786438436991_0.5350165288474"},"_hasShrinkwrap":false}},"time":{"created":"2026-08-11T07:07:09.213Z","modified":"2026-08-11T08:53:57.280Z","0.3.0":"2026-08-11T07:07:09.593Z","0.3.1":"2026-08-11T08:53:57.133Z"},"bugs":{"url":"https://github.com/AKR1166/Rules-MCP/issues"},"license":"MIT","homepage":"https://github.com/AKR1166/Rules-MCP#readme","keywords":["mcp","rules","ai-governance","cursor","claude","vscode","antigravity"],"repository":{"type":"git","url":"git+https://github.com/AKR1166/Rules-MCP.git"},"description":"AI Governance MCP — structured skills, knowledge, and evaluation for Cursor, Claude, VS Code, and Antigravity","maintainers":[{"name":"akr1166org","email":"thumuruachyuth@gmail.com"}],"readme":"# Rules MCP\r\n\r\nAI Governance MCP: one source of truth for **Markdown/MDC skills**, knowledge, and evaluation — usable from **Cursor**, **Claude**, and any MCP-compatible agent.\r\n\r\n> Status: **Phase 2 — AI governance** (`0.3.0`) — **complete**  \r\n> Content format: **MD / MDC only** under `cursor skills/` (YAML rules deprecated)\r\n\r\n## What this is\r\n\r\nMaintain Cursor-style skills as `.md` / `.mdc` under `cursor skills/`. Agents discover them through MCP (`list_skills`, `get_skill`, `search_skills`), enrich prompts, and pull context — without depending on YAML rule files.\r\n\r\nSee [implementation.md](./implementation.md) for the full roadmap.\r\n\r\n## Phase 2 (current)\r\n\r\n| Capability | Status |\r\n|------------|--------|\r\n| Skill Engine (MD/MDC under `cursor skills/`) | ✅ |\r\n| Knowledge / Context / Prompt engines | ✅ |\r\n| Violation pipeline + plugin validators | ✅ (optional; no YAML seed rules) |\r\n| Diff review / scorecard / explain | ✅ |\r\n| Ranked knowledge search | ✅ |\r\n| Full artifact suite + 7 agent profiles | ✅ |\r\n| HTTP org server / IDE extension | Phase 3 |\r\n\r\n### Tools\r\n\r\n- `ping`, `server_info`\r\n- `list_skills`, `get_skill`, `search_skills` ← **primary content API**\r\n- `list_rules`, `get_rule`, `search_rules` (legacy YAML path; empty by default)\r\n- `get_knowledge`, `search_knowledge`, `get_context`, `enrich_prompt`\r\n- `validate_code`, `validate_paths`, `review_diff`, `score_output`, `explain_violation`\r\n- `generate_artifacts`\r\n\r\n### Skills layout\r\n\r\n```\r\ncursor skills/\r\n  typescript-expert/SKILL.md\r\n  nestjs-best-practices/SKILL.md\r\n  nestjs-best-practices/rules/*.md\r\n  ...\r\n```\r\n\r\n### Profiles\r\n\r\n`default`, `cursor`, `claude`, `continue`, `cline`, `gemini`, `chatgpt`\r\n\r\n## Quick start\r\n\r\n```bash\r\nnpm install\r\nnpm run build\r\nnpm test\r\nnpm run rules:validate\r\n```\r\n\r\n### Install globally (recommended for other IDEs)\r\n\r\nMakes `rules-mcp` available on your PATH for Cursor, VS Code, Antigravity, Claude Desktop, etc.:\r\n\r\n```bash\r\nnpm run link:global\r\nrules-mcp version\r\n```\r\n\r\nThen point any MCP client at:\r\n\r\n```json\r\n{\r\n  \"command\": \"rules-mcp\",\r\n  \"args\": [\"serve\"]\r\n}\r\n```\r\n\r\nSee [docs/CONNECT.md](./docs/CONNECT.md) for VS Code, Antigravity, and other clients.  \r\nUnlink later with `npm run unlink:global`.\r\n\r\nValidate / score / review:\r\n\r\n```bash\r\nrules-mcp validate \"const x: any = 1;\" --file=src/x.ts\r\nrules-mcp score \"const x: any = 1;\" --file=src/x.ts\r\nrules-mcp review-diff --stdin < change.patch\r\n```\r\n\r\nGenerate all artifacts:\r\n\r\n```bash\r\nrules-mcp generate --out=.\r\n# or subset:\r\nrules-mcp generate --target=cursor,agents,claude,styleguide,security --out=.\r\n```\r\n\r\nStart the MCP server:\r\n\r\n```bash\r\nrules-mcp serve\r\n# or: npm start\r\n```\r\n\r\nConnect a client: [docs/CONNECT.md](./docs/CONNECT.md)  \r\nNatural-language prompts: [docs/USER_PROMPTS.md](./docs/USER_PROMPTS.md)  \r\nEvaluate Phase 2: [docs/PHASE2_EVAL.md](./docs/PHASE2_EVAL.md)\r\n\r\n## Layout\r\n\r\n```\r\nrules/            # Enforceable governance rules (YAML)\r\ncursor skills/    # Cursor agent skills (Markdown / MDC)\r\nknowledge/        # Project knowledge\r\nprofiles/         # Per-agent profiles (7+)\r\nsrc/              # MCP server + engines + validator plugins\r\nexamples/         # Client MCP configs\r\ndocs/             # Connect + phase eval\r\nFirst phase/      # Phase 0 archive\r\n```\r\n\r\n## Environment\r\n\r\n| Variable | Default |\r\n|----------|---------|\r\n| `RULES_PATH` | `./rules` |\r\n| `SKILLS_PATH` | `./cursor skills` |\r\n| `KNOWLEDGE_PATH` | `./knowledge` |\r\n| `PROFILES_PATH` | `./profiles` |\r\n| `PROFILE` | `default` |\r\n| `LOG_LEVEL` | `info` |\r\n\r\n## License\r\n\r\nMIT\r\n","readmeFilename":"README.md"}