> ## Documentation Index
> Fetch the complete documentation index at: https://modem.dev/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Skills for MCP Clients

> How the Modem MCP server teaches your MCP client to use its tools

**Skills** are short instructions that the Modem MCP server gives your MCP client. Each one covers one group of Modem tools: when to use them, in what order, and what to check in the result.

There is nothing to install. When you [connect the server](/docs/api/modem-mcp-server), your client gets a `modem_skills` tool that returns them.

<Info>
  These are not [Agent Skills](/docs/features/skills) in **Settings → Skills**. Those are instructions you write for the Modem Agent inside
  Modem. The skills on this page ship with the MCP server, and your MCP client reads them.
</Info>

## How your client finds them

The descriptions of `search_modem`, `modem_agent_invoke`, and the write tools each end by naming the skill to read before the first call. Your client calls `modem_skills` with that name and gets the whole skill back.

When your client calls `modem_skills` with no `name`, the result lists every skill and says which tool fits which task.

The server has three skills:

* `search-modem` covers asking `search_modem` a question, paging through results, and telling a complete result from a partial one.
* `agent-runs` covers starting a Modem Agent run, polling for the result, following up, and cancelling.
* `write-tools` covers finding IDs before a write, confirming merges with you, and reading partial results.

The [MCP Tool Reference](/docs/api/mcp-tools#modem_skills) documents the `modem_skills` parameters and result.

## Skills and scopes

The scopes you approve decide which tools your client can call. `search_modem` needs `data:read`. The agent run tools and the write tools need `agent:invoke`.

Skills have no such limit. A client with either scope can read all three.

A skill can therefore name a tool your client does not have, and it explains what to do in that case. The `agent-runs` skill, for example, tells a client that has `data:read` alone to ask you to re-authorize with `agent:invoke` before it starts a run.

## Related

<CardGroup cols={2}>
  <Card title="Modem MCP Server" icon="https://mintcdn.com/modem-844d7a4a/Wr2r4IRr97lNQiQb/icons/link.svg?fit=max&auto=format&n=Wr2r4IRr97lNQiQb&q=85&s=e774d33588635d44c6c935b78ed55f13" href="/docs/api/modem-mcp-server" width="24" height="24" data-path="icons/link.svg">
    Connect the server in Claude Code, Cursor, VS Code, Codex, and other clients.
  </Card>

  <Card title="MCP Tool Reference" icon="https://mintcdn.com/modem-844d7a4a/Wr2r4IRr97lNQiQb/icons/book.svg?fit=max&auto=format&n=Wr2r4IRr97lNQiQb&q=85&s=c166962d701f09f1375a1312739d93eb" href="/docs/api/mcp-tools" width="24" height="24" data-path="icons/book.svg">
    Parameters, results, and examples for every MCP tool.
  </Card>

  <Card title="The Modem Agent" icon="https://mintcdn.com/modem-844d7a4a/Wr2r4IRr97lNQiQb/icons/bot-bolt.svg?fit=max&auto=format&n=Wr2r4IRr97lNQiQb&q=85&s=dda761a2f7042ebc27c668cc644df76c" href="/docs/features/agent" width="22" height="22" data-path="icons/bot-bolt.svg">
    What the Modem Agent can query and do.
  </Card>

  <Card title="Agent Skills" icon="https://mintcdn.com/modem-844d7a4a/Wr2r4IRr97lNQiQb/icons/bot.svg?fit=max&auto=format&n=Wr2r4IRr97lNQiQb&q=85&s=2496f9106cb54fa9f4e27ad1f8f3a171" href="/docs/features/skills" width="22" height="22" data-path="icons/bot.svg">
    Instructions you write for the Modem Agent in Settings → Skills.
  </Card>
</CardGroup>