Find, install, and use artifacts.

metahub is a registry of small, focused capabilities you can drop into the AI tools you already use (Claude Code, Cursor, Antigravity, and other clients that support the underlying formats). Each capability is called an artifact. Artifacts come in four flavors (skills, MCP servers, agents, and plugins), and the registry handles all of them under one roof.

You don't need an account to browse. You don't need an account to install public artifacts. Sign in only if you want personalized installs, the ability to leave reviews, or to publish your own.

An artifact is a small, self-contained package that gives an AI tool a new ability. Think of it like a browser extension, but for the AI in your editor or terminal.

For example:

• A skill called pdf teaches your AI client how to read and summarize PDF files.
• An MCP server called filesystem lets your client read and write files within a sandboxed directory.
• An agent called code-reviewer can be invoked from your Node app to leave inline PR comments.
• A plugin bundles several skills + an MCP server into a single install: for example, a complete frontend-dev kit.

Pick the right kind for what you're trying to do. The kind determines where the files land on your machine and how Claude invokes them.

skillintent-triggered

A markdown file with a frontmatter trigger. Claude reads it when the conversation matches the description. Best for narrow, well-scoped tasks: "summarize a PDF," "convert image to webp," "explain SQL plan."

mcptool server

A long-lived process exposing tools over the Model Context Protocol. Claude can call those tools any time. Best for external system access: filesystem, GitHub API, database, browser automation.

agentNode import

A reusable TypeScript agent you import into your own code. Best for headless automation: code review, ticket triage, scheduled batch jobs.

pluginbundle

A grouping of skills + an MCP server + a settings file, installed as one unit. Best for cohesive toolkits like "Python data work" or "frontend development."

The fastest way to use metahub is to plug its MCP server into the AI tool you already have open. Once installed, you can ask your AI things like “find me a skill for parsing PDFs” or “what metahub artifacts do I have installed?”, no terminal step.

Pick your client and copy the snippet:

Want to script installs, automate from CI, or pin versions in dotfiles? Use the CLI below.

Use this for CI, scripts, and reproducible setups. The MCP server is the faster path for interactive use.

mh is a tiny Node CLI that handles install, list, update, and uninstall. It works on macOS, Linux, and Windows (WSL). You need Node 20 or newer.

npm install -g @metahub/cli
mh --version

mh login

Three ways to find what you need:

1. Browse the registry at /browse, then filter by kind, tag, freshness, or popularity.
2. Search by keyword:
   bash

   mh search pdf
   mh search "image conversion"
   mh search --kind=mcp database

3. Inspect details before installing:
   bash

   mh show skills/pdf

   Prints the artifact's description, version, repo URL, published SHA, tags, and recent star rating.

One command:

mh install skills/pdf
# or
mh install mcps/filesystem
mh install agents/code-reviewer
mh install plugins/frontend-dev

The CLI will:

1. Fetch the published SHA from the registry
2. Download the source from GitHub
3. Place files at the conventional path for that kind
4. Wire any required hooks (MCP settings, plugin manifest)
5. Mint a per-install API key and store it at ~/.metahub/installs.json

mh list

Once installed, artifacts are invoked by the host AI tool; you don't usually call them by hand.

skills

Just ask your AI tool something that matches the skill's description. If you installed skills/pdf, say "summarize this PDF" and the host (Claude Code, Cursor, etc.) picks it up automatically.

MCP servers

Tools are available as soon as your client restarts. Claude will offer them when a tool call is appropriate; no special trigger phrase needed.

agents

Import into your Node code and call the agent's exported function. The artifact's README has the exact snippet.

plugins

Work like the sum of their parts: skills behave like skills, the MCP behaves like an MCP, all from one install.

Each install is pinned to the SHA that was published. You won't wake up to a broken artifact because the author force-pushed; updates are explicit.

mh update skills/pdf          # update one artifact
mh update --all               # update everything
mh outdated                   # show what has newer versions available

To remove an artifact:

mh uninstall skills/pdf

The CLI removes the files, scrubs the MCP server entry, and revokes the per-install API key.

Every artifact has a 1–5 star rating and a threaded review feed. Open the artifact's detail page and scroll down, or click Write a review to leave one of your own.

Reviews flow back to the developer's dashboard within seconds. Developers can hide individual reviews from their portal, but they can't edit them or filter by rating.

When an artifact is invoked, the bundled SDK reports a small amount of usage data back to the developer who published it. You can audit exactly what's collected and turn it off any time.

mh config set telemetry off          # disable ingest entirely
mh config set telemetry-handoff off  # keep invocations, drop handoff graph

skill not loading

Restart your AI tool: skills are read at launch, not hot-reloaded. Confirm the file exists at the tool's skills directory (e.g. ~/.claude/skills/<slug>/SKILL.md for Claude Code).

MCP not connecting

Run mh doctor mcps/<slug>: it spawns the MCP server in foreground and reports the stderr if it crashes. 90% of the time it's a missing env var.

install fails with 404

The artifact may have been unpublished. Run mh search <slug> to confirm it's still in the registry, then mh cache clear and retry.

permission denied on global install

Either use a node version manager (asdf, fnm, nvm), or install with a user prefix: npm config set prefix ~/.npm-global && export PATH=$PATH:~/.npm-global/bin.