Install Skillibary in your agent
This page covers a single goal: get an MCP-compatible agent (Claude Desktop, Cursor, Continue) talking to the public Skillibary registry. After you finish, the agent gains four tools and can search and load any verified skill on demand.
What gets installed
Four tools become available to the agent once the server is wired up:
| Tool | When the agent calls it |
|---|---|
search_skills | To answer “what skill could help here?” Returns summaries, no full content. |
get_skill | Once it has picked a candidate, to read the full SKILL.md. Use counter increments in the background. |
list_skills | To browse by tag when search isn't the right tool. |
get_skill_stats | Usage counters for a specific skill, last 7 and 30 days. |
Submitting and re-verifying skills is intentionally not exposed through MCP. Those operations require your GitHub account, which the agent doesn't have. Use the web submit form or the CLI's publish command for that flow.
Add the config
Paste this block into your agent's MCP config (file locations below). No environment variables are required.
{
"mcpServers": {
"skillibary": {
"command": "npx",
"args": ["-y", "skillibary-mcp"]
}
}
}The -y flag tells npx to install the package without an interactive prompt. Without it, the first run can hang waiting for confirmation that the agent never sees.
Where each client stores its config
Claude Desktop
| OS | Path |
|---|---|
| macOS | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Windows | %APPDATA%\\Claude\\claude_desktop_config.json |
If the file doesn't exist yet, create it with a single empty object {} and paste the mcpServers key inside.
Cursor
Open Settings, navigate to Features → MCP, click “Add MCP Server”, and paste the skillibary block (just the inner object, not the outer mcpServers wrapper). Cursor restarts the server automatically when you save.
Continue (VS Code)
Edit ~/.continue/config.json. The mcpServers key lives at the top level of the config object, with the same shape shown above. Reload the VS Code window to pick up the change.
Verifying the install
Open a new chat in your client and ask:
What MCP tools do you have available right now?
You should see four tools listed with names prefixed by skillibary. If the agent says it has no MCP tools, or lists tools from other servers but not Skillibary, jump to the troubleshooting section below.
Example agent prompts
Once the tools are present, the agent picks them up on its own:
Find a Skillibary skill that helps write good git commit messages.
Use the skillibary "pdf-extract" skill to pull text from this attached PDF.
List the top three Skillibary skills tagged "sql" by use count.
Two calls happen under the hood. First the agent invokes search_skills with the query, reads the summaries, and picks one. Then it calls get_skill with the id from the search result. The skill body lands in the agent's context, the use counter goes up by one, and the agent answers from the skill text.
Pointing at a self-hosted registry
Running your own Skillibary instance? Set SKILLIBARY_REGISTRY in the MCP config and the server will hit your URL instead of the public one:
{
"mcpServers": {
"skillibary": {
"command": "npx",
"args": ["-y", "skillibary-mcp"],
"env": {
"SKILLIBARY_REGISTRY": "https://your-instance.example.com"
}
}
}
}See Self-hosting for how to stand up a registry from scratch.
Troubleshooting
The agent doesn't see any skillibary tools
- You refreshed instead of restarted. Claude Desktop keeps the old subprocess running. Fully quit and relaunch.
- JSON syntax error. A trailing comma or missing quote in the config silently disables the whole
mcpServersblock. Runcat claude_desktop_config.json | jq. If jq rejects it, your client did too. - npx is not on the agent's PATH. Common on macOS when Node was installed through a version manager (nvm, fnm, asdf). Easiest fix: replace
"command": "npx"with the absolute path returned bywhich npxin your shell.
Tools listed, but every call returns an error
The MCP server prints diagnostic output to stderr; your client's log panel shows it.
| Error fragment | What it means |
|---|---|
Registry network error | The server can't reach the registry. Check that you're online and that https://skillibary.com resolves. |
Registry 429 | You hit the per-IP search rate limit (30/min). Slow down or wait a minute. |
Not found from get_skill | The id doesn't exist or the skill isn't verified. Search again and use the id from the fresh result. |
Registry 5xx | Registry-side outage. Check status page or try again later. |
The agent picks the wrong skill
Semantic search returns the closest match by cosine similarity, not by exact name. Two ways to help:
- Be specific in the prompt. “Find a skill that summarises PDFs into bullet points” beats “help me with this PDF”.
- Mention the slug. If you already know which skill you want, name it: “Use the skillibary ‘pdf-extract’ skill…”. The agent will search for that name, find it as the top hit, and load it directly.
Uninstalling
Remove the skillibary entry from your client's MCP config and restart the client. The npx cache will still hold the package, but it stays inert until the config references it. To purge the cache entirely: npx clear-npx-cache.