URL: /developers/agents/cursor

---
title: "squirrelscan for Cursor"
sidebarTitle: "Cursor"
description: "Set up squirrelscan in Cursor: one-click MCP install, add the skills, and run audits from chat or the agent."
icon: "mouse-pointer-click"
---

Cursor gets squirrelscan as a one-click MCP install plus the audit skills. Cursor can then run audits, read findings as tools, and fix them across your codebase.

## 1. Install the CLI

The skills and local audits run through the `squirrel` binary.

```bash
curl -fsSL https://install.squirrelscan.com | bash
```

Local audits are free and run entirely on your machine. Verify with `squirrel --version`.

## 2. Add the MCP server

<Tabs>
  <Tab title="One-click (recommended)">
    Click [**Add to Cursor**](https://squirrelscan.com/add/cursor). Cursor opens, shows an approval dialog, and writes the server into your `mcp.json`.
  </Tab>
  <Tab title="Manual">
    Add it to `~/.cursor/mcp.json` (global) or `.cursor/mcp.json` (this project). A remote server only needs a `url`, Cursor auto-negotiates the transport:

    ```json
    {
      "mcpServers": {
        "squirrelscan": {
          "url": "https://mcp.squirrelscan.com/mcp"
        }
      }
    }
    ```
  </Tab>
</Tabs>

<Note>Don't add a `"type"` field to a remote (`url`) entry, it's only for stdio servers. API-key auth and CLI details are on the [MCP client setup](/developers/mcp-clients#cursor) page.</Note>

## 3. Authenticate (for cloud)

Local audits need nothing. For hosted crawling, publishing, and credits, open **Settings → Customize** (labelled **Tools & Integrations** in some builds), find **squirrelscan**, and click **Needs login** to run the browser flow. From the Cursor CLI: `agent mcp login squirrelscan`.

## 4. Install the skills

The MCP server exposes tools; the skills add autonomous audit-and-fix workflows. Cursor supports the Agent Skills standard natively, and also loads skills from Claude Code's directories.

```bash
npx skills add squirrelscan/squirrelscan
```

## 5. Run an audit

In chat or the agent, trigger the skill:

```
/audit-website
```

Cursor detects your project's website and runs the audit. Or be explicit, or use natural language:

```
/audit-website https://example.com then fix all issues across the codebase
```

```
Use the audit-website skill to audit example.com and fix the accessibility issues.
```

<Tip>Use the agent (composer) for multi-file fixes so Cursor can edit across the codebase in one pass.</Tip>

## Next steps

<CardGroup cols={2}>
  <Card title="Fix your site with an AI agent" icon="wand-sparkles" href="/guides/fix-your-site-with-an-ai-agent">
    A full worked example of the audit-and-fix loop.
  </Card>
  <Card title="Hosted MCP server" icon="plug" href="/developers/mcp">
    The full tool list, auth, and credits.
  </Card>
  <Card title="MCP client setup" icon="toy-brick" href="/developers/mcp-clients#cursor">
    Scopes, API-key auth, and JSON config.
  </Card>
  <Card title="Rules reference" icon="list-checks" href="/rules">
    Every audit rule and how it's fixed.
  </Card>
</CardGroup>