Menulis satu file capabilities.yaml ke dalam format config native dari 35+ AI coding agent dan mem-proxy MCP server upstream melalui local gateway.
Juga dikenal sebagai infragate/capa
- Stars
- 747
- Tools
- —
- Unduhan, 30 hari
- —
- Versi terbaru
- —
- Commit terakhir
- 7 Nov 2026
- Lisensi
- MIT
Apa itu CAPA MCP?
Menulis satu file capabilities.yaml ke dalam format config native dari 35+ AI coding agent dan mem-proxy MCP server upstream melalui local gateway.
Ringkasan dibuat dari README proyek
Tentang CAPA MCP server
Mengelola konfigurasi AI agent di berbagai coding tool yang berbeda adalah hal yang disederhanakan oleh capa bagi para developer. CAPA bertindak sebagai package manager pusat dan local gateway yang mengonversi satu file capabilities.yaml menjadi format native yang dibutuhkan oleh lebih dari 35 agent berbeda, termasuk Cursor, Claude Code, Windsurf, dan GitHub Copilot. Dengan menggunakan satu sumber kebenaran (single source of truth), tim dapat memastikan bahwa setiap kolaborator menggunakan tool, rules, dan sub-agent yang sama persis melalui file capabilities.lock yang mengunci SHA spesifik.
Selain konfigurasi, CAPA berfungsi sebagai MCP gateway yang mem-proxy server upstream melalui stdio, HTTP, atau SSE. Setup ini memungkinkan lazy-loading tool sesuai kebutuhan, yang dapat mengurangi penggunaan token sebesar 19% hingga 40%. Developer dapat mengelola seluruh setup mereka melalui Web UI lokal atau command line, menggunakan perintah wrap untuk menjalankan agent seperti Codex atau Gemini CLI di dalam shadow workspace agar repositori utama Anda tetap bersih.
Apa yang bisa Anda lakukan dengannya
- 1Sinkronisasi konfigurasi agentDistribusikan toolset dan rules yang identik ke seluruh anggota tim hanya dengan melakukan commit pada satu file konfigurasi.
- 2Mengurangi konsumsi tokenTurunkan biaya inferensi dengan memuat tool hanya saat dibutuhkan, alih-alih mengirimkan seluruh katalog ke model.
- 3Isolasi izin sub-agentBatasi akses tool tertentu agar tidak dapat diakses oleh sub-agent tertentu guna mencegah tindakan yang tidak disengaja.
- 4Menjaga kebersihan repositoriJalankan AI coding agent di dalam shadow workspace sehingga folder konfigurasi spesifik provider tidak mengotori proyek Anda.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Pengecekan otomatis
Berjalan 14 Nov 2026Laporan lengkap →Belum diverifikasi. Sebuah server memerlukan skor 80, tidak ada temuan serius, dan data yang cukup untuk kami periksa. Cara kerja checks · Yang perlu diperbaiki untuk menambah poin
- Source repository terhubung dan dapat dijangkauinfragate/capa is public and reachablegithub.com/infragate/capa ↗Lolos
- Nama paket mencantumkan repositori ini sebagai sumbernyaTidak diperiksa
- Provenance build (atestasi Sigstore)Tidak diperiksa
- Lisensi open source (OSI)MITspdx.org/licenses/MIT.html ↗Lolos
- Ada commit atau release dalam satu tahun terakhirLast commit or release 2026-11-07github.com/infragate/capa ↗Lolos
- OpenSSF ScorecardTidak diperiksa
- Nama package tidak mirip dengan package populerTidak diperiksa
- Tidak ada advisory kritis pada paket atau dependensinyaTidak diperiksa
- 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 GitHubDeclare skills, tools, rules, sub-agents, MCP servers, hooks, and plugins once in capabilities.yaml. Run capa install. CAPA writes them into Cursor, Claude Code, Codex, Windsurf, GitHub Copilot, and 35+ other agents — native formats, pinned SHAs, zero manual sync. At runtime it is also the MCP gateway: every agent talks to one local endpoint; CAPA proxies upstream servers, lazy-loads tools, and scopes what each sub-agent can call.
https://github.com/user-attachments/assets/200a8cf9-7236-4cc0-a9e4-332bb6664b41
Why CAPA?
Agent config today is scattered across CLAUDE.md, .cursor/rules/, AGENTS.md, MCP JSON, hooks, and skill folders. No two teammates match. Nothing is pinned. Cloning the repo does not clone the agent setup.
CAPA collapses that into one version-controlled file next to your code — and a local MCP gateway in front of every tool:
capabilities.yaml— source of truth for every capabilitycapabilities.lock— SHA pins so tomorrow's clone gets the same bytes- Marker blocks — surgical writes that leave hand-edited content alone
- MCP gateway — one endpoint per project; CAPA proxies stdio / HTTP / SSE servers, applies formatters, and records activity
The teammate who clones tomorrow gets the exact setup you have today.
Features
- One file → 35+ agents — write once; CAPA fans out to each provider's native layout (
.cursor/rules/,.claude/agents/,AGENTS.md, …) - MCP gateway — one local endpoint per agent; CAPA proxies upstream MCP servers, lazy-loads tools on demand, and filters tools per sub-agent
- Cheaper inference, same quality — on-demand tool loading instead of front-loading the whole catalog (19–40% fewer tokens across 150 trials on claude-opus-4-8)
capa wrap— run Cursor, Claude, Codex, and more from a shadow workspace so provider dirs never touch your real repo- Local Web UI — interactive capabilities editor with live YAML sync, registry browse, OAuth setup, and drag-to-reorder
- Activity traces — live feed of every MCP call, shell tool, and agent span on the project page
- Plugins that unpack — Claude and Cursor plugins decompose into skills, MCP, rules, sub-agents, and hooks
- Registries — browse skills.sh, Cursor Marketplace, Claude plugins, and Claude marketplace catalogs
capa add --passthrough— write provider-native files directly when you want unmanaged one-offs- Sub-agent isolation — each sub-agent gets a filtered MCP endpoint, so research agents never inherit a
git pushtool
Installation
macOS and Linux:
curl -LsSf https://capa.sh/install.sh | sh
Windows:
powershell -ExecutionPolicy ByPass -c "irm https://capa.sh/install.ps1 | iex"
Quick start
1. Initialize
cd your-project
capa init
Creates capabilities.yaml and registers the project with the local CAPA server (default http://localhost:5912).
The new file points at the JSON Schema, so editors with YAML/JSON language support autocomplete and validate it. For an existing file, add this first line:
# yaml-language-server: $schema=https://raw.githubusercontent.com/infragate/capa/main/schema/capabilities.schema.json
2. Add capabilities
capa add vercel-labs/agent-skills@web-researcher
capa add --server --id brave --cmd npx --arg @brave/brave-search-mcp
capa registry search skills-sh "research"
3. Install
capa install # interactive: confirms executable surface, then installs
capa install --yes # CI / scripts: skip confirmation
capa install --dry-run # preview MCP servers, hooks, and commands without changes
Resolves SHAs, fills the cache, writes per-provider files, and registers one MCP endpoint with each configured agent. Resolved SHAs land in capabilities.lock.
[!NOTE] Non-interactive shells (CI, scripts) must pass
--yes. The first install prints the executable surface (MCP stdio servers, hooks, command tools, plugins) and asks for confirmation; unchanged surfaces skip the prompt on re-run.
[!TIP] Already have skills, MCP configs, and rules in the repo? After
capa init, use the bundled/bootstrapskill — the agent scans the project and drafts the CAPA config for you.
4. Run tools from the terminal
capa sh # list every configured tool
capa sh brave # list brave subcommands
capa sh brave search --query "…" # run a tool directly
capa sh --raw brave search --query "…" # skip per-tool formatters
Every tool you define is also a CLI command under capa sh.
5. Open the Web UI
capa open # open this folder's project in the browser
capa open ../other # or any other project folder
capa status # prints the local URL when the server is up
Edit skills, tools, rules, hooks, plugins, and agents in the browser. Changes sync live back to capabilities.yaml.
capa wrap
Run an agent without polluting your repo with .cursor/, .claude/, and friends. CAPA builds a shadow workspace under ~/.capa/workspaces/, symlinks your project (minus provider-owned paths), installs capabilities into the shadow, and launches the agent.
capa wrap cursor # Cursor GUI — stops when the window closes
capa wrap claude # Claude Code (aliases: claude-code)
capa wrap agent # Cursor CLI
capa wrap codex
capa wrap gemini-cli
capa wrap opencode
capa wrap cursor --print-dir # print shadow path, then launch
capa wrap --prune # clean stale workspaces
capa stop # stop server + active wrap sessions
Wrappable today: Claude Code, Codex, Cursor, Gemini CLI, OpenCode, iFlow CLI, Kiro CLI, Qwen Code, Kimi CLI.
[!NOTE] On Windows, creating the shadow workspace may require Developer Mode (or an elevated shell) for symlinks. GitHub Copilot is not wrappable yet — it owns shared
.github//.vscode/trees that need subpath exclusions.
Web UI & observability
The embedded React UI (served by the local server) covers the full project lifecycle:
| Area | What you get |
|---|---|
| Capabilities editor | Skills, tools, rules, hooks, sub-agents, plugins, agents — CRUD, local file pickers, drag reorder |
| Registries | Search seeded catalogs (skills.sh, Cursor Marketplace, Claude plugins) and add your own |
| Activity | Live tool-call feed, charts, and run timelines (default-on via options.agentActivity) |
| Variables / OAuth | Credential setup when install needs secrets |
Activity is powered by system hooks and the MCP proxy tracer — MCP failures show as error rows, shell tools from capa sh are labeled correctly, and secrets in args/results are redacted.
Plugins & registries
Plugins are not opaque blobs. CAPA clones the repo, reads Claude (.claude-plugin/) or Cursor (.cursor-plugin/) manifests, and merges skills, MCP servers, rules, sub-agents, and hooks into the same install pipeline as everything else.
capa add owner/repo --plugin --install
capa add cursor-marketplace:some-plugin --plugin
capa registry list
capa registry add anthropics/claude-plugins-official --type claude-marketplace
capa registry search skills-sh "typescript"
[!IMPORTANT] Most registry adapters are executable TypeScript fetched into
~/.capa/registries-managed/. Review the source before enabling a third-party registry. Claude marketplaces are JSON catalogs only — safer by design.
Passthrough mode
Need a one-off native write without CAPA managing the file?
capa add owner/repo@skill --passthrough --provider cursor
capa add --rule --id ts-strict --inline "Always use strict TypeScript" --passthrough
capa install --passthrough
Passthrough skips capabilities.yaml, the lockfile, and managed-file tracking. Tool aliases, defaults, and formatters still require managed mode (capa add --tool … --passthrough is refused).
How it fits together
capabilities.yaml ──► capa install ──► provider files (.cursor/, .claude/, AGENTS.md, …)
│ │
│ ├── capabilities.lock
│ ├── ~/.capa/cache/ (content-addressed snapshots)
│ └── ~/.capa/db.sqlite (projects, variables, activity)
│
└──► Web UI editor ◄──► file watcher ◄──► disk
Agent ──MCP──► capa gateway (:5912) ──proxy──► upstream MCP (stdio / HTTP / SSE)
│
├── on-demand tools (setup_tools / call_tool)
├── per-sub-agent filtered endpoints
└── ToolCallTracer → activity feed
CLI cheat sheet
capa init # create capabilities.yaml + register project
capa add <source> [--plugin] [--install]
capa add --server|--tool|--rule|--hook …
capa install [-p <provider>] [-e .env] [--no-cache] [--yes] [--dry-run]
capa wrap <provider> [--project <path>]
capa sh [tool] [args…] [--raw]
capa registry search|add|list|refresh|remove …
capa start|stop|restart|status
capa clean # remove managed artifacts
capa auth github|gitlab
capa cache | capa cache clean
capa upgrade [--yes] # pin GitHub release + verify installer checksum
Documentation
Guides, the full schema reference, and the registry catalog:
Maintainer-oriented internals (install pipeline, provider matrix, lockfile semantics) live in docs/.
Community
- @InfragateAI: release notes, new providers, and CAPA tips
- @AntonioZaitoun: built by Antonio Zaitoun; follow along for what's next
Questions or bugs? Open an issue.
Pertanyaan tentang CAPA MCP
Apa kegunaan CAPA bagi AI coding agent?
CAPA membaca satu file capabilities.yaml dan menuliskan skill, tool, rules, sub-agent, MCP server, serta plugin ke dalam layout native masing-masing agent. CAPA juga menjalankan local MCP gateway di depan server upstream.
AI coding agent apa saja yang didukung oleh CAPA?
CAPA mendistribusikan konfigurasi ke Cursor, Claude Code, Codex, Windsurf, GitHub Copilot, dan lebih dari 35 agent lainnya. Perintah capa wrap juga dapat menjalankan Claude Code, Codex, Cursor, Gemini CLI, OpenCode, dan beberapa lainnya dalam shadow workspace.
Bagaimana cara install CAPA?
Pada macOS dan Linux gunakan curl install script; pada Windows gunakan PowerShell one-liner. Setelah itu, jalankan capa init di proyek Anda untuk membuat capabilities.yaml.
Apakah CAPA mengurangi penggunaan token?
Ya. MCP gateway memuat tool sesuai kebutuhan (on demand) alih-alih memuat seluruh katalog di awal, yang menurut README dapat mengurangi penggunaan token sebesar 19–40% berdasarkan 150 uji coba.
Bagaimana cara menjalankan tool yang sudah dikonfigurasi dari terminal?
Setiap tool yang Anda definisikan akan menjadi perintah CLI di bawah capa sh. Lihat daftar tool dengan capa sh, lalu jalankan subcommand seperti capa sh brave search --query "…".