Squirrelscan MCP Server

squirrelscan

The website QA tool for your coding agent

squirrelscan audits your website for SEO, performance, security, accessibility and agent experience issues, and gives your coding agent exact fixes. Run it from the CLI, inside your coding agent, in the cloud, or over MCP. Local audits are always free.

Add to your coding agent

squirrelscan ships as skills (autonomous audit + fix workflows), an MCP server (hosted at mcp.squirrelscan.com), and a plugin for Claude Code and Cursor. Pick your agent:

Cursor

One click: the Add to Cursor badge above, or add the MCP server manually to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "squirrelscan": { "type": "http", "url": "https://mcp.squirrelscan.com/mcp" }
  }
}

Skills install with npx skills add squirrelscan/squirrelscan.

Claude Code

Install the plugin (bundles skills + the MCP server):

/plugin marketplace add squirrelscan/squirrelscan
/plugin install squirrelscan@squirrelscan

Or add just the MCP server:

claude mcp add --transport http squirrelscan https://mcp.squirrelscan.com/mcp

Any MCP client

squirrelscan is in the MCP Registry as com.squirrelscan/squirrelscan. Point any client at the remote server:

https://mcp.squirrelscan.com/mcp

Authentication is per-user OAuth (or pass a squirrelscan API key as a Bearer token).

OpenAI Codex / other agents

Skills follow the Agent Skills standard. Install with npx skills add squirrelscan/squirrelscan (lands in .agents/skills/), or clone this repo and symlink the skills/* directories.

Features

• 260+ Rules, 21 Categories - Comprehensive coverage across SEO, accessibility, performance, and security
• AI-Native Design - LLM-optimised output for Claude Code, Cursor, and any AI assistant
• Smart Incremental Crawling - ETag, Last-Modified, content hashing. Resume from checkpoints.
• Developer-First CLI - Single binary, zero dependencies, shell completions, self-update
• E-E-A-T Auditing - Dedicated rules for Experience, Expertise, Authority, Trust
• Crawl History & Changes - Track site evolution, compare crawls, spot regressions
• Multiple Output Formats - Console, JSON, HTML, Markdown, Text, LLM, XML

CLI

Installation

macOS / Linux:

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

Windows:

iwr -useb https://install.squirrelscan.com/install.ps1 | iex

npm (all platforms):

npm install -g squirrelscan

npx (run without installing):

npx squirrelscan audit example.com

Quick Start

# Audit a website
squirrel audit https://example.com

# Generate HTML report
squirrel audit https://example.com -f html -o report.html

# Pipe to Claude for AI analysis
squirrel audit https://example.com --format llm | claude

# Limit pages for faster results
squirrel audit https://example.com -m 10

Skills

Two skills drive agent workflows:

• squirrelscan - operating the CLI: install, login, keys, credits, running audits, publishing reports, MCP setup, config, troubleshooting.
• audit-website - the full fix loop: audit, map issues to source files, fix in batches, re-audit until the site scores well.

npx skills add squirrelscan/squirrelscan

Then, in your agent:

Use the audit-website skill to audit this site and fix all issues but only crawl 10 pages

Rule Categories

Total: 261 rules across 21 categories

See the rules reference for full details.

Output Formats

Development Status

squirrelscan is in active beta. Expect rapid iteration and breaking changes. Feedback and issue reports welcome!

Links

• Website
• Documentation
• AI Agent Integration
• Share Feedback
• Bugs, Issues & Feature Requests
• Twitter/X

License

The skills, plugin manifests, MCP configuration, and install scripts in this repository are MIT licensed (see LICENSE). The squirrelscan CLI binary itself is distributed as a standalone executable and is not open source.