Memungkinkan AI client untuk melakukan validasi, lint, diff, dan konversi file agent skill di berbagai IDE seperti Cursor, Claude, dan VS Code.
Juga dikenal sebagai ModelBound/modelbound-mcp-server, modelbound-mcp-server
- Stars
- 1
- Tools
- —
- Unduhan, 30 hari
- —
- Versi terbaru
- 0.1.2
- Commit terakhir
- 13 Okt 2026
- Lisensi
- MIT
Apa itu ModelBound MCP?
ModelBound adalah MCP server. Memungkinkan AI client untuk melakukan validasi, lint, diff, dan konversi file agent skill di berbagai IDE seperti Cursor, Claude, dan VS Code.
Ringkasan dibuat dari README proyek
Tentang ModelBound MCP server
Mengelola agent skills di berbagai lingkungan AI adalah fungsi utama dari modelbound-mcp bagi developer yang menggunakan tool seperti Cursor, Claude, Windsurf, dan VS Code. MCP server berbasis local-first ini memungkinkan Anda untuk melakukan validasi, lint, diff, dan konversi file skill agar aturan dan konteks Anda tetap portabel antar platform. Server ini berjalan secara lokal melalui stdio dan tidak memerlukan akun atau API key untuk operasi lokal dasar.
Pengguna dapat melakukan pemindaian keamanan offline menggunakan tool flightCheck untuk mendeteksi risiko injeksi, secrets, atau perintah destruktif. Server ini juga menyediakan tool khusus seperti skills.convert untuk menerjemahkan file antar format IDE dan skills.lint untuk memeriksa broken links atau jumlah token. Jika Anda memilih untuk menggunakan opsi cloud sync dengan MODELBOUND_API_KEY, Anda akan mendapatkan akses ke cloud.pushSkill, cloud.pullSkill, dan cloud.search untuk mengelola skill Anda di dalam tim atau di beberapa mesin.
Apa yang bisa Anda lakukan dengannya
- 1Konversi skill antar IDETerjemahkan aturan yang ditulis untuk Cursor ke dalam format yang kompatibel dengan Claude.
- 2Lakukan pemindaian keamanan offlineJalankan flight check untuk memastikan agent skills Anda tidak mengandung perintah berbahaya atau secrets.
- 3Validasi kepatuhan file skillPeriksa apakah file skill Anda memenuhi standar format agentskills.io.
- 4Sinkronisasi skill ke cloudPush aturan agent lokal Anda ke repositori remote untuk akses tim menggunakan API key.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Cara menginstal ModelBound MCP
Format diverifikasi 10 Nov 2026Tambahkan ke CursorTambahkan ke GooseInstal ModelBound MCP di Claude Code
$ claude mcp add --env 'MODELBOUND_API_KEY=<YOUR_MODELBOUND_API_KEY>' modelbound-mcp-server -- npx -y modelbound-mcpInstal ModelBound MCP di Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"modelbound-mcp-server": {
"command": "npx",
"args": [
"-y",
"modelbound-mcp"
],
"env": {
"MODELBOUND_API_KEY": "<YOUR_MODELBOUND_API_KEY>"
}
}
}
}Instal ModelBound MCP di VS Code
.vscode/mcp.json
{
"servers": {
"modelbound-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"modelbound-mcp"
],
"env": {
"MODELBOUND_API_KEY": "<YOUR_MODELBOUND_API_KEY>"
}
}
}
}Instal ModelBound MCP di VS Code CLI
$ code --add-mcp '{"name":"modelbound-mcp-server","type":"stdio","command":"npx","args":["-y","modelbound-mcp"],"env":{"MODELBOUND_API_KEY":"<YOUR_MODELBOUND_API_KEY>"}}'Instal ModelBound MCP di Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"modelbound-mcp-server": {
"command": "npx",
"args": [
"-y",
"modelbound-mcp"
],
"env": {
"MODELBOUND_API_KEY": "<YOUR_MODELBOUND_API_KEY>"
}
}
}
}Instal ModelBound MCP di Codex
$ codex mcp add modelbound-mcp-server --env 'MODELBOUND_API_KEY=<YOUR_MODELBOUND_API_KEY>' -- npx -y modelbound-mcpInstal ModelBound MCP di Codex config.toml
~/.codex/config.toml
[mcp_servers.modelbound-mcp-server] command = "npx" args = ["-y", "modelbound-mcp"] [mcp_servers.modelbound-mcp-server.env] MODELBOUND_API_KEY = "<YOUR_MODELBOUND_API_KEY>"
Instal ModelBound MCP di Gemini CLI
$ gemini mcp add -s user -e 'MODELBOUND_API_KEY=<YOUR_MODELBOUND_API_KEY>' modelbound-mcp-server npx -- -y modelbound-mcpInstal ModelBound MCP di Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"modelbound-mcp-server": {
"command": "npx",
"args": [
"-y",
"modelbound-mcp"
],
"env": {
"MODELBOUND_API_KEY": "<YOUR_MODELBOUND_API_KEY>"
}
}
}
}Konfigurasi
MODELBOUND_API_KEYRahasiaModelBound API key for optional cloud sync features. Get one at https://modelbound.co/settings/api-keys
| Nama | Deskripsi | Tipe |
|---|---|---|
| MODELBOUND_API_KEY | ModelBound API key for optional cloud sync features. Get one at https://modelbound.co/settings/api-keys | Rahasia |
Pengecekan otomatis
Berjalan 13 Nov 2026Laporan lengkap →Lolos checks otomatis kami. Ini bukan audit keamanan: baca kodenya dan berikan server akses paling terbatas yang dibutuhkannya. Cara kerja checks
- Source repository terhubung dan dapat dijangkaumodelbound/modelbound-mcp-server is public and reachablegithub.com/modelbound/modelbound-mcp-server ↗Lolos
- Nama paket mencantumkan repositori ini sebagai sumbernyamodelbound-mcp names modelbound/modelbound-mcp-server as sourcenpmjs.com/package/modelbound-mcp ↗Lolos
- Provenance build (atestasi Sigstore)No build attestation published for this releaseTidak diperiksa
- Lisensi open source (OSI)MITspdx.org/licenses/MIT.html ↗Lolos
- Ada commit atau release dalam satu tahun terakhirLast commit or release 2026-10-13github.com/modelbound/modelbound-mcp-server ↗Lolos
- OpenSSF ScorecardTidak diperiksa
- Nama package tidak mirip dengan package populerNo popular package one edit away from modelbound-mcpLolos
- Tidak ada advisory kritis pada paket atau dependensinya109 resolved dependencies checked; no critical advisoryosv.dev ↗Lolos
- Tidak ada instruksi tersembunyi untuk model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersLolos
- Tools yang bersifat destruktif telah diberi labelTidak diperiksa
- Endpoint remote merespons handshake MCPTidak diperiksa
README
Lihat di GitHubmodelbound-mcp
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.
Why ModelBound?
AI 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.
What it does
modelbound-mcp is a small Model Context Protocol server you run locally over stdio. It exposes tools to your IDE / agent using dot-notation naming for navigable discovery:
Local (no API key, no network):
ide.detectLayout— find which IDE conventions your repo usesskills.listLocal,skills.readLocal,skills.writeLocalskills.lint— front-matter, token count, broken links, TODO scan, pass / warn / fail checks (scanner h5)skills.flightCheck— Flight Check offline safety scan (injection, exfiltration, secrets, destructive commands, wildcard tools, loop hazards); same rules asnpx modelbound checkskills.checks— deterministic safety/quality checks without full lint (no numeric score)skills.scaffold— create a skill with default scope constraintsskills.reviewStatus,skills.reviewRequest,skills.reviewApprove,skills.reviewReject,skills.reviewGateskills.validateFormat— agentskills.io complianceskills.convert— translate between IDE formats (e.g. Cursor → Claude)skills.diff— compare a local skill with its cloud counterpart
Cloud (with MODELBOUND_API_KEY):
cloud.pullSkill,cloud.pushSkill,cloud.searchcloud.listSkills— now acceptsai_typeandsource_platformfilters; every row includesai_type,source_platform,source_path, andrepocloud.resourceTree— returns the team's full hierarchy grouped by platform → top-level dir (.claude/skills,.cursor/rules,.kiro/steering, …) → files. Use this beforecloud.listSkillswhen an orchestrator needs to map context before loading.cloud.installMarketplaceSkilloptimization.health
Resource hierarchy
Orchestrators 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.
The 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.
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.
Anti-slop (0.4.x) — trust scanner bumped to h5 with scope-limit, unbounded-wording, dependency, and refactor findings.
skills.readLocalnow returnschecks,scanner_version,review_state, andreview_meta. Override default scope limits via.modelbound/task-budgets.json. Useskills.reviewGatein CI to block unapproved skills.
Install
npx modelbound-mcp
Or install globally:
npm i -g modelbound-mcp
Use as an MCP server
Cursor (.cursor/mcp.json)
{
"mcpServers": {
"modelbound": {
"command": "npx",
"args": ["-y", "modelbound-mcp"],
"env": { "MODELBOUND_API_KEY": "mb_live_..." }
}
}
}
MODELBOUND_API_KEY is optional. Without it, local tools still work.
See examples/ for Claude Desktop, Kiro, Windsurf, and VS Code configs.
Use as a CLI
modelbound-mcp detect # which IDE layouts exist here?
modelbound-mcp ls # list every skill file
modelbound-mcp lint .cursor/rules/ # lint a directory
modelbound-mcp lint .codex/skills/ # lint Codex skills
modelbound-mcp validate ./SKILL.md # agentskills.io compliance
modelbound-mcp convert --from cursor --to claude ./rule.mdc > out.md
Tests
npm test # unit tests (registry parity, checks, review, harness)
npm run smoke # local MCP tools + CLI subcommands (+ cloud if MODELBOUND_API_KEY set)
npm run test:e2e # offline anti-slop / review lifecycle
CLI vs MCP tool mapping: docs/PARITY.md.
Contributing
We want help. Specifically:
- New IDE adapters — Zed, Aider, Continue, JetBrains AI, Cline. See CONTRIBUTING.md for the ~50 line recipe.
- Linter rules — token estimation accuracy, dead-link detection, format-specific gotchas.
- Format converters — fidelity improvements between adapter pairs.
Browse good first issues and the roadmap.
Related projects
| Project | Description |
|---|---|
| ModelBound CLI · npm | Terminal + CI for token optimization, skill pipeline, and version management |
| Cursor Extension · Marketplace | VS Code/Cursor extension for rules sync and MCP bridge |
| Cursor Plugin | Cursor slash commands for pipeline, safety checks, and versions |
| Claude Code Plugin | Claude Code plugin for pipeline, hooks, and skill sync |
| Dev Packs | Open-source curated AI context packs for engineering teams |
Also on Smithery (stdio via npx modelbound-mcp) and the MCP Registry. Install hub: modelbound.co/connect
License
MIT © ModelBound
Pertanyaan tentang ModelBound MCP
Bagaimana cara menambahkan ModelBound MCP ke Claude Code?
Jalankan claude mcp add --env 'MODELBOUND_API_KEY=<YOUR_MODELBOUND_API_KEY>' modelbound-mcp-server -- npx -y modelbound-mcp di terminal Anda. Tambahkan --scope user agar tersedia di semua proyek.
Bagaimana cara menambahkan ModelBound MCP ke Cursor?
Buka ~/.cursor/mcp.json dan tambahkan server di bawah mcpServers, menggunakan config Cursor yang ditunjukkan di bagian instalasi di atas.
Bisakah saya menggunakan ModelBound tanpa API key?
Ya, tool lokal dapat berfungsi tanpa API key, meskipun fitur cloud memerlukannya.
IDE apa saja yang didukung?
Mendukung Cursor, Claude, Codex, Kiro, Windsurf, VS Code, dan Amazon Q.
Bagaimana cara menyinkronkan skill saya di berbagai AI tool?
ModelBound memungkinkan Anda menulis satu skill dan menyinkronkannya ke berbagai platform agar tidak terkunci pada satu IDE saja.