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

# Use Skill Doctor as an MCP server in your AI agent

> Register Skill Doctor as a Model Context Protocol server in Claude Code, Claude Desktop, Cursor or Windsurf so your agent audits skills and tools before it loads or edits them.

Run as an MCP server, Skill Doctor lets your agent scan a skill before it loads, runs or modifies it.

> [tab] Claude Code
>
> ```bash theme={null}
> claude mcp add skill-doctor -- npx -y @security.kalarislabs/skill-doctor mcp
> ```

> [tab] Cursor, Windsurf, Claude Desktop
>
> Add this entry to your `mcp.json` or the agent's MCP settings:
>
> ```json mcp.json theme={null}
> {
>   "mcpServers": {
>     "skill-doctor": {
>       "command": "npx",
>       "args": ["-y", "@security.kalarislabs/skill-doctor", "mcp"]
>     }
>   }
> }
> ```

> [tab] Ask your agent
>
> Paste this into your coding agent:
>
> > Please install `@security.kalarislabs/skill-doctor` and register it as an MCP server with command
> > `npx -y @security.kalarislabs/skill-doctor mcp`. Use it to audit skill files and tools in this
> > workspace before executing or modifying them.

Restart the agent after you change its MCP configuration.

> [!TIP]
>
> If you installed with cargo, run `skill-doctor mcp` directly and make sure the binary was built with
> `--features mcp`. See [installation](https://docs.kalarislabs.com/skill-doctor/getting-started/installation.md).

## Scanner hijacking protection

A malicious skill can try to instruct the agent that called the scanner. Skill Doctor fences scanned content
before it returns results, and tracks these attempts as threat class
[SD-11](https://docs.kalarislabs.com/skill-doctor/reference/threat-classes.md).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.