Writes one capabilities.yaml into 35+ AI coding agents' native config formats and proxies upstream MCP servers through a local gateway.
Also known as infragate/capa
- Stars
- 747
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 7, 2026
- License
- MIT
What is CAPA MCP?
CAPA writes one capabilities.yaml into 35+ AI coding agents' native config formats and proxies upstream MCP servers through a local gateway.
Summary generated from the project's README
About CAPA MCP server
Managing AI agent configurations across different coding tools is what capa simplifies for developers. It acts as a central package manager and local gateway that converts a single capabilities.yaml file into the native formats required by over 35 different agents, including Cursor, Claude Code, Windsurf, and GitHub Copilot. By using a single source of truth, teams can ensure that every collaborator uses the exact same tools, rules, and sub-agents through a capabilities.lock file that pins specific SHAs.
Beyond configuration, it serves as an MCP gateway that proxies upstream servers via stdio, HTTP, or SSE. This setup allows for lazy-loading tools on demand, which can reduce token usage by 19% to 40%. Developers can manage their entire setup through a local Web UI or the command line, using the wrap command to run agents like Codex or Gemini CLI within shadow workspaces to keep their primary repositories clean.
What you can do with it
- 1Synchronize agent configurationsDistribute identical toolsets and rules to all team members by committing a single configuration file.
- 2Reduce token consumptionLower inference costs by loading tools only when they are needed rather than sending the entire catalog to the model.
- 3Isolate sub-agent permissionsRestrict specific tools from being accessible to certain sub-agents to prevent accidental actions.
- 4Protect repository cleanlinessRun AI coding agents in a shadow workspace so that provider-specific configuration folders do not clutter your project.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableinfragate/capa is public and reachablegithub.com/infragate/capa ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-07github.com/infragate/capa ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on 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.
CAPA MCP questions
What does CAPA do for AI coding agents?
It reads a single capabilities.yaml and writes skills, tools, rules, sub-agents, MCP servers, and plugins into each agent's native layout. It also runs a local MCP gateway in front of upstream servers.
Which AI coding agents does CAPA support?
CAPA fans out to Cursor, Claude Code, Codex, Windsurf, GitHub Copilot, and over 35 other agents. capa wrap can also launch Claude Code, Codex, Cursor, Gemini CLI, OpenCode, and several others in a shadow workspace.
How do I install CAPA?
On macOS and Linux use the curl install script; on Windows use the PowerShell one-liner. Then run capa init in your project to create capabilities.yaml.
Does CAPA reduce token usage?
Yes. The MCP gateway loads tools on demand instead of front-loading the whole catalog, which the README reports as 19–40% fewer tokens across 150 trials.
How do I run a configured tool from the terminal?
Every tool you define becomes a CLI command under capa sh. List tools with capa sh, then run a subcommand such as capa sh brave search --query "…".