siteone-mcp-server
Enables SEO auditing and site analysis by crawling websites, identifying issues, and generating reports like sitemaps and markdown exports.
README
siteone-mcp-server
MCP server that wraps the SiteOne Crawler CLI for SEO auditing and site analysis. Use it with Claude Code, Claude Desktop, or any MCP-compatible client.
Install SiteOne Crawler
The auto-installer downloads the correct SiteOne Crawler binary for your platform:
npx -y siteone-mcp-server --install
This installs to ~/.siteone-crawler/ and the MCP server will auto-detect it — no further configuration needed.
Supports macOS (arm64, x64) and Linux (arm64, x64). Windows users should download manually.
Quick Start
Claude Code
claude mcp add siteone -- npx -y siteone-mcp-server
Claude Desktop
Add to your MCP settings (~/.claude/mcp_settings.json):
{
"mcpServers": {
"siteone": {
"command": "npx",
"args": ["-y", "siteone-mcp-server"]
}
}
}
Available Tools
| Tool | Description |
|---|---|
crawl_site |
Full site crawl — returns JSON with SEO, performance, and security metrics for all URLs |
crawl_single_page |
Single page analysis — fast, lightweight audit of one URL |
generate_sitemap |
Crawl a site and generate an XML sitemap file |
export_markdown |
Crawl a site and export all pages as markdown files |
get_crawl_summary |
Quick shallow crawl for health check statistics |
Configuration
The server resolves the SiteOne binary in this order:
--siteone-binCLI argument (highest priority)SITEONE_BINenvironment variable~/.siteone-crawler/crawler(auto-installed location)crawlerin PATH (fallback)
CLI argument
claude mcp add siteone -- npx -y siteone-mcp-server --siteone-bin=/path/to/crawler
Or in Claude Desktop config:
{
"mcpServers": {
"siteone": {
"command": "npx",
"args": ["-y", "siteone-mcp-server", "--siteone-bin=/path/to/crawler"]
}
}
}
Environment variables
| Variable | Purpose | Default |
|---|---|---|
SITEONE_BIN |
Path to the SiteOne crawler binary | Auto-detected (see above) |
SITEONE_OUTPUT_DIR |
Working directory for crawl outputs | Current working directory |
Examples
Once configured, ask Claude:
- "Crawl https://example.com and summarize the SEO issues"
- "Check if https://example.com has any broken links"
- "Generate a sitemap for https://example.com"
- "Export https://example.com as markdown"
- "Give me a quick health check of https://example.com"
Development
# Install dependencies
npm install
# Build
npm run build
# Watch mode
npm run dev
# Test with MCP Inspector
npm run inspect
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.