{
  "markdown": "# modelbound-mcp\n\n> Local-first MCP server for agent skills. Validate, lint, diff, and convert agent skill files across Cursor, Claude, Codex, Kiro, Windsurf, VS Code, and Amazon Q — no account required. Optional cloud sync with [ModelBound](https://modelbound.co).\n\n[![npm](https://img.shields.io/npm/v/modelbound-mcp.svg)](https://www.npmjs.com/package/modelbound-mcp)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n[![ModelBound Skill Trust](https://modelbound.co/api/badge/skills.svg?repo=ModelBound/modelbound-mcp-server)](https://modelbound.co/connect/github-actions?repo=ModelBound/modelbound-mcp-server)\n\n## Why ModelBound?\n\nAI tools come and go. You might use Cursor today, switch to Claude Code tomorrow, and try Kiro next week — but your skills, rules, and context shouldn't be locked into any one of them. ModelBound gives you a single place to store and manage your agent skills, so you can move between tools freely without rebuilding your setup each time. Write a skill once, sync it everywhere, and get more value out of every AI subscription you're already paying for.\n\n## What it does\n\n`modelbound-mcp` is a small [Model Context Protocol](https://modelcontextprotocol.io) server you run locally over stdio. It exposes tools to your IDE / agent using **dot-notation naming** for navigable discovery:\n\n**Local (no API key, no network):**\n- `ide.detectLayout` — find which IDE conventions your repo uses\n- `skills.listLocal`, `skills.readLocal`, `skills.writeLocal`\n- `skills.lint` — front-matter, token count, broken links, TODO scan, trust score (scanner **h5**)\n- `skills.trust` — deterministic slop/trust heuristics without full lint\n- `skills.scaffold` — create a skill with default scope constraints\n- `skills.reviewStatus`, `skills.reviewRequest`, `skills.reviewApprove`, `skills.reviewReject`, `skills.reviewGate`\n- `skills.validateFormat` — agentskills.io compliance\n- `skills.convert` — translate between IDE formats (e.g. Cursor → Claude)\n- `skills.diff` — compare a local skill with its cloud counterpart\n\n**Cloud (with `MODELBOUND_API_KEY`):**\n- `cloud.pullSkill`, `cloud.pushSkill`, `cloud.search`\n- `cloud.listSkills` — now accepts `ai_type` and `source_platform` filters; every row includes `ai_type`, `source_platform`, `source_path`, and `repo`\n- `cloud.resourceTree` — returns the team's full hierarchy grouped by platform → top-level dir (`.claude/skills`, `.cursor/rules`, `.kiro/steering`, …) → files. Use this before `cloud.listSkills` when an orchestrator needs to map context before loading.\n- `cloud.installMarketplaceSkill`\n- `optimization.health`\n\n### Resource hierarchy\n\nOrchestrators that juggle multiple AI platforms can call `cloud.resourceTree` once to get a complete map of available skills, rules, hooks, steering files, and system prompts — grouped exactly how each platform expects them on disk. Pair it with the new `ai_type` / `source_platform` filters on `cloud.listSkills` to load only the slice you need. See [`examples/resource-tree.ts`](./examples/resource-tree.ts).\n\nThe cloud tools are a thin JSON-RPC proxy to `mcp.modelbound.co`. All business logic stays server-side; this repo never touches your data or secrets.\n\n> **Migration from 0.1.x** — old snake_case names (`detect_ide_layout`, `pull_skill`, …) were removed in 0.2.0. The hosted ModelBound MCP server still accepts both forms forever for backward compatibility.\n\n> **Anti-slop (0.4.x)** — trust scanner bumped to **h5** with scope-limit, unbounded-wording, dependency, and refactor findings. `skills.readLocal` now returns `trust_score`, `scanner_version`, `review_state`, and `review_meta`. Override default scope limits via `.modelbound/task-budgets.json`. Use `skills.reviewGate` in CI to block unapproved skills.\n\n## Install\n\n```bash\nnpx modelbound-mcp\n```\n\nOr install globally:\n\n```bash\nnpm i -g modelbound-mcp\n```\n\n## Use as an MCP server\n\n### Cursor (`.cursor/mcp.json`)\n\n```json\n{\n  \"mcpServers\": {\n    \"modelbound\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"modelbound-mcp\"],\n      \"env\": { \"MODELBOUND_API_KEY\": \"mb_live_...\" }\n    }\n  }\n}\n```\n\n`MODELBOUND_API_KEY` is optional. Without it, local tools still work.\n\nSee [`examples/`](./examples) for Claude Desktop, Kiro, Windsurf, and VS Code configs.\n\n## Use as a CLI\n\n```bash\nmodelbound-mcp detect                                  # which IDE layouts exist here?\nmodelbound-mcp ls                                      # list every skill file\nmodelbound-mcp lint .cursor/rules/                     # lint a directory\nmodelbound-mcp lint .codex/skills/                     # lint Codex skills\nmodelbound-mcp validate ./SKILL.md                     # agentskills.io compliance\nmodelbound-mcp convert --from cursor --to claude ./rule.mdc > out.md\n```\n\n## Contributing\n\nWe want help. Specifically:\n\n- **New IDE adapters** — Zed, Aider, Continue, JetBrains AI, Cline. See [CONTRIBUTING.md](CONTRIBUTING.md) for the ~50 line recipe.\n- **Linter rules** — token estimation accuracy, dead-link detection, format-specific gotchas.\n- **Format converters** — fidelity improvements between adapter pairs.\n\nBrowse [good first issues](https://github.com/ModelBound/modelbound-mcp-server/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22) and the [roadmap](ROADMAP.md).\n\n## Related projects\n\n| Project | Description |\n| --- | --- |\n| [ModelBound CLI](https://github.com/ModelBound/modelbound-cli) · [npm](https://www.npmjs.com/package/modelbound) | Terminal + CI for token optimization, skill pipeline, and version management |\n| [Cursor Extension](https://github.com/ModelBound/modelbound-cursor-extension) · [Marketplace](https://marketplace.visualstudio.com/items?itemName=ModelBound.modelbound-cursor-extension) | VS Code/Cursor extension for rules sync and MCP bridge |\n| [Cursor Plugin](https://github.com/ModelBound/cursor-plugin) | Cursor slash commands for pipeline, trust & safety, and versions |\n| [Claude Code Plugin](https://github.com/ModelBound/modelbound-claude-code-plugin) | Claude Code plugin for pipeline, hooks, and skill sync |\n| [Dev Packs](https://github.com/ModelBound/dev-packs) | Open-source curated AI context packs for engineering teams |\n\nAlso on [Smithery](https://smithery.ai) (stdio via `npx modelbound-mcp`) and the [MCP Registry](https://github.com/ModelBound/modelbound-mcp-server/blob/main/server.json). Install hub: [modelbound.co/connect](https://modelbound.co/connect)\n\n## License\n\nMIT © ModelBound\n",
  "bytes": 6457,
  "sha": "0e87c79135bf69701c686caa5ec192aa9dfef295e64bdd8da58773b13f82becd",
  "repo_slug": "modelbound/modelbound-mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_modelbound_modelbound_mcp_6ed49be4/readme"
}