crawlseo MCP
crawlseo MCP compares the latest 28 days of site metrics with the preceding 28 days, alongside results from the latest crawl.
- 674 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The read key exposes account sites’ metrics, search queries and crawl data to the connected agent.
Install
- Works in
Manual install
claude mcp add crawlseo -e CRAWLSEO_URL=http://localhost:3000 -e CRAWLSEO_API_KEY=<key> -- npx -y @crawlseo/mcpConnects the stdio server to Claude Code. Substitute your crawlseo URL and key locally without putting the key in chat.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The read key exposes account sites’ metrics, search queries and crawl data to the connected agent.
This is third-party code. Review the repository files before installing.
What it does
crawlseo MCP connects an agent to stored SEO-monitoring data. It reads search queries, pages and traffic trends along with technical crawl results. Separate tools expose performance metrics and potential improvements. The server uses the selected crawlseo instance’s API without a direct database connection. A key is scoped to its account’s sites. Tools cannot start crawls, trigger synchronization or write changes.
Who it is for. SEO practitioners with a running crawlseo instance who discuss their sites’ stored metrics with an agent.
Good fit when
- A specialist uses stored impressions to find low-click-through pages.
- Issues from the latest crawl are prioritized.
- A performance regression is related to a particular page’s metrics.
- Google and Bing search data are analyzed in one conversation.
Not a fit when
- You need to trigger crawling or change a site directly through MCP.
- No crawlseo instance or connected data sources exist.
- You need unauthorized access to another account’s sites.
Example request
Use the latest completed crawlseo crawl to show major issues and pages to inspect first, without launching jobs.MCP
- Transport
- stdio, http
- Authentication
- API key
Environment variables
CRAWLSEO_URL- URL of your crawlseo instance.
CRAWLSEO_API_KEYrequired, secret- Account data read key.
Limitations
MCP reads stored results, so freshness depends on crawlseo’s crawl and synchronization schedules. Search Console and Bing connect separately; metrics for an unconnected source will be missing. Each remote HTTP client must send its own key or the server refuses access. Queries and pages can reveal site strategy, so share them only with an authorized model and inspect the resulting report before publishing it.
How to disable. Disable MCP or revoke the key in crawlseo settings, then remove the client connection. Platform crawl and synchronization schedules remain separate.
FAQ
How many tools are documented?
The README tool table lists 12 tools. Start with the site list, choose your site, then request the required period or the latest completed crawl.
Which transports are supported?
stdio and streamable HTTP. A crawlseo instance also provides its own `/mcp` endpoint.
Where do I obtain a key?
In Settings > MCP after enabling access. The value is shown once and can be revoked there.
What period does the overview compare?
The latest 28 days against the preceding 28 days, alongside the latest crawl and performance data.
Why can Bing differ from Google’s daily reports?
Some Bing tools aggregate queries and pages by week. Account for the reporting periods when comparing them.
Discussion
No questions or reviews yet.
Related
MCP serversSearch Console MCP: Google, Bing and GA4 data for agents
Search Console MCP
An MCP server that gives an agent Google Search Console, Bing Webmaster, GA4 and AdSense data with ready SEO checks
An MCP server with SEO data: backlinks, keyword difficulty and traffic estimates from the free Ahrefs tools
Google Search Console MCP
Google Search Console MCP Server for SEOs
An MCP server for Google Search Console: queries and pages with clicks and positions, URL indexing checks, sitemaps and ready SEO skills
DataForSEO MCP filters API responses to selected fields, so an agent receives only the data needed for the current analysis.
SEO CLI and MCP
seo-cli
The seo command and an MCP server for SEO work: page audits, Search Console, analytics and keywords. Sign-in through Google
An MCP server retrieves Semrush keyword, domain and backlink data so an agent can compare competitors and prepare SEO analysis.
README in short
The platform stores sites and tokens in its own PostgreSQL and supports schedules. Optional DataForSEO access adds keyword and backlink data; Google Autocomplete suggestions are available without it.