Squirrelscan MCP server
{
"mcpServers": {
"squirrelscan": {
"type": "http",
"url": "https://mcp.squirrelscan.com/mcp"
}
}
}{
"mcpServers": {
"squirrelscan": {
"type": "http",
"url": "https://mcp.squirrelscan.com/mcp"
}
}
}{
"mcpServers": {
"squirrelscan": {
"type": "http",
"url": "https://mcp.squirrelscan.com/mcp"
}
}
}{
"servers": {
"squirrelscan": {
"type": "http",
"url": "https://mcp.squirrelscan.com/mcp"
}
}
}{
"mcpServers": {
"squirrelscan": {
"type": "http",
"url": "https://mcp.squirrelscan.com/mcp"
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 1.0.2
What it does
squirrelscan is an open source website audit tool that checks for issues across SEO, performance, security, accessibility, and agent experience. It runs as a CLI tool or over MCP and provides coding agents with specific fixes for detected problems.
- Audit a website for SEO compliance, broken links, crawlability issues, and structured data problems before deployment.
- Check how well a site works with AI agents by verifying agent-accessible content, AGENTS.md presence, and API discoverability.
- Scan for security vulnerabilities including phishing signatures, leaked credentials, HTTPS configuration, and mixed content issues.
Tools this server exposes
| Tool | Does |
|---|---|
| audit_website | Crawl and audit a website against 279 rules across 21 categories including SEO, performance, security, accessibility, and agent experience, returning specific i |
| compare_crawls | Compare two website crawl results to identify regressions, changes, and new issues. |
| crawl_resume | Resume an interrupted crawl from a checkpoint using incremental crawling with ETag and content hashing. |
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.