Best for
- Founders, indie developers, and small teams
- Users who want self-hosted SEO tools with data privacy
- Users who want to leverage AI assistants for quick SEO insights
C
CrawlSEO MCP Server
Community
Open-source SEO monitoring: Google Search Console + Site Crawler + Core Web Vitals + MCP Server in one self-hosted dashboard.
GitHub source repository ↗
57FMRS · C
The CrawlSEO MCP Server is part of the CrawlSEO platform, enabling AI agents (such as Claude Code, Claude Desktop, and Cursor) to query your SEO data directly. It provides 10 tools covering site listing, overview, keyword and page data, traffic metrics, crawl and audit, Core Web Vitals, and SEO opportunities. The server runs over stdio transport and requires a locally running CrawlSEO instance with proper environment configuration.
Tools
list_sites
List all added sites.
get_site_overview
Get overview data for a specific site.
get_keywords
Get keyword rankings and performance data.
get_pages
Get page performance data.
get_traffic
Get traffic statistics.
run_crawl
Trigger a crawl of the site.
get_crawl_status
Get the status of the most recent crawl.
get_crawl_issues
Get issues found during the crawl.
get_vitals
Get Core Web Vitals (LCP, CLS, INP, etc.).
get_opportunities
Get SEO opportunities (e.g., low CTR, content decay).
Setup
- Clone the repo:
git clone https://github.com/crawlseo/crawlseo.gitand enter the directory. - Install dependencies:
npm install. - Configure environment: copy
.env.exampleto.env.localand setDATABASE_URL,NEXTAUTH_SECRET,GOOGLE_CLIENT_ID, andGOOGLE_CLIENT_SECRET. - Start the database (e.g., with Docker):
docker compose up -d db. - Run migrations:
npx prisma migrate dev --name init. - Start the app:
npm run dev. - Configure the MCP server in a supported client (e.g., Claude Desktop) by adding the install_config JSON.
claude_desktop_config.json
{
"mcpServers": {
"crawlseo": {
"command": "npx",
"args": [
"tsx",
"mcp/server.ts"
],
"cwd": "/path/to/crawlseo"
}
}
}
Fit and risk
Not for
- Users needing advanced enterprise-grade SEO features (e.g., large-scale keyword research, paid data)
- Non-technical users, as self-hosting and configuration require technical skills
- Users requiring official support (this is an open-source community project)
Required permissions
- Requires access to the local server's database (PostgreSQL)
- Requires Google OAuth credentials to access Google Search Console data
- Requires network access to run crawls and fetch Core Web Vitals (e.g., via PageSpeed Insights)
Risks and side effects
- Data security risk: if the self-hosted instance is exposed to the internet without proper protection, data leakage may occur.
- Dependence on third-party services (Google, PageSpeed Insights, DataForSEO) for availability and quota limits.
- Open-source software may have unknown vulnerabilities; you must maintain and update it yourself.
- Misconfiguration can prevent it from working, such as missing environment variables or a down database.
Troubleshooting
- Ensure `.env.local` is configured and all required environment variables are set.
- Ensure PostgreSQL is running and accessible, with `DATABASE_URL` correct.
- Run `npx prisma migrate dev` to initialize the database schema.
- Check app logs for errors; ensure all dependencies are installed.
- Check MCP configuration file path and command in your client.
Use cases
Query SEO data in natural language from your terminal, without opening the dashboard.
Let AI agents automatically analyze keyword performance, page issues, and generate optimization suggestions.
Integrate SEO monitoring into your existing AI workflows for automated reporting.
Supported clients
Claude DesktopFull support