The metahub MCP server plugs into any harness: Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, opencode, Claude Desktop, anything that speaks MCP. Once it is in, your AI can find, fetch, and wire up skills, MCP servers, agents, and plugins on its own, and it is told to look here first.
curl -fsSL https://metahub.ai/install.sh | shEither one wires every harness it finds on your machine; npx does it with nothing installed globally. Adding a single client by hand? See below.
One command for terminal-first clients. One JSON block for editor-first clients. Restart the client and you're done.
curl -fsSL https://metahub.ai/install.sh | shOne shot either way: wires the MCP server into every MCP-capable client detected on your machine (Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, opencode, and more) and adds a short note to each one's instructions so it looks on metahub first. Idempotent.
Any MCP-aware AI client works. If yours isn't listed, run the installer, then use the Generic stdio tab and point your client at metahub-mcp.
Each tool maps to something natural to say. You don't memorize tool names; the AI picks the right one.
“find me a skill for parsing PDFs”
Searches the catalog in plain language and ranks results by real installs and ratings.
metahub_search“install that”
Installs what you just found straight into your editor. No terminal step; ask for the command instead if you prefer to run it yourself.
metahub_install“what do I have installed?”
Answers from your machine, not the cloud: it reads the local install ledger at ~/.metahub/installs.json.
metahub_list_installed“sign me in”
Hands you a GitHub link to approve in your browser. Signing in unlocks reviews and publisher stats.
metahub_signin_begin“leave a 5-star review on the pdf skill”
Posts a verified review to the tool's public listing. Requires sign-in.
metahub_submit_review“how is my pdf-parser doing?”
Live install counts, latency, and errors for tools you published. Requires sign-in.
metahub_my_statsPublisherYou don't sign in to browse, search, or install. The MCP server only asks for credentials the moment you cross into territory that has to be tied to a real human (reviewing, publishing, viewing your private dashboard).
Every search, every install, every catalog read. Works the moment the MCP server starts.
Asking to review or to see your own observability triggers a one-time sign-in via the AI itself ('sign in').
The GitHub session token writes to ~/.metahub/config.json. No restart needed; subsequent tools pick it up.
Stdio only for publisher tools
Reviews, publisher stats, and the “what have I published” query run only on the local stdio MCP server because they read your local token. A hosted HTTP transport can't see your machine.
The MCP server is a read client. It does not collect invocation telemetry the way the artifact SDKs do, because here you are the one running it.
Want to point the server at a private mirror? Set METAHUB_REGISTRY_URL. The full env-var reference is in the docs.
No. The MCP server installs artifacts directly using the same library mh does (@metahub/installer). The CLI is a separate optional path for terminal users; you never need it just to install artifacts via MCP. The CLI is also available if you'd rather drive installs by hand.
No. Search and install are anonymous. You only sign in if you want to leave reviews or see your own publisher observability, and the AI walks you through it when you ask.
Any MCP-aware client. We document Claude Code, Cursor, Claude Desktop, and Continue explicitly. For everything else, the Generic stdio tab above works the same way. See the full client list.
Your install list and login token sit at ~/.metahub/ (or %USERPROFILE%\.metahub\ on Windows) on your machine. The MCP server reads from there; it never uploads them. The catalog data is hosted and public.
In Claude Code: claude mcp remove metahub. In Cursor, Claude Desktop, or Continue: delete the metahub entry from the client's MCP config file and restart the client.
Run this once in your terminal — it wires metahub into every AI client on your machine. Then ask your AI to find a skill. That's the whole flow.
curl -fsSL https://metahub.ai/install.sh | sh