MCP server that exposes OnCrawl's API for use with Claude Code and Claude Desktop
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"oncrawl-mcp-server","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# OnCrawl MCP Server [](https://badge.fury.io/py/oncrawl-mcp-server) [](https://opensource.org/licenses/MIT) MCP server that exposes OnCrawl's API for use with Claude Code and Claude Desktop. Enables Claude to perform deep technical SEO analysis by querying crawl data, Google Search Console metrics, and crawl-over-crawl comparisons. ## Features - **12 MCP Tools** for comprehensive SEO analysis - **Raw data access**: Query pages, links, clusters, structured data with flexible OQL - **Schema discovery**: Claude learns available fields before querying - **Aggregations**: Group/count by any dimension for pattern detection - **Full exports**: No 10k limit for complete datasets - **Crawl-over-crawl analysis**: Track changes between crawls (new pages, status changes, etc.) - **Google Search Console integration**: 600+ GSC fields including clicks, impressions, CTR, position by device, brand/non-brand, and more - **Google Analytics 4 integration**: Session, user, and engagement metrics ## What Makes This Powerful OnCrawl combines crawl data with GSC/GA4 traffic data, enabling analyses like: - **Orphan pages with traffic**: Pages getting clicks from Google but not linked internally - **Underlinked high-performers**: Popular pages with weak internal linking - **Low CTR opportunities**: Pages with high impressions but poor click-through rates - **404s still in Google**: Broken pages still appearing in search results - **Deep pages with traffic**: Buried content that Google values - **Mobile vs desktop performance**: Traffic breakdowns by device ## Prerequisites - Python 3.11+ - OnCrawl account with API access - OnCrawl API token (from your OnCrawl settings) ## Installation ### Option 1: Install from PyPI (Recommended) ```bash pip install oncrawl-mcp-server ``` Then configure in Claude Desktop/Code (see [Configuration](#configuration))…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.