CrawlCoach developer docs
Connect an AI agent to CrawlCoach with MCP. Your agent reads your fix list and the pages Google left out, fixes them in your project, and asks CrawlCoach to recheck them with Google.
Your sitemap lists the pages you want on Google. Google Search Console's URL Inspection data says which ones Google has. CrawlCoach compares the two, shows which pages Google left out and why, and gives the fix for each one.
MCP (Model Context Protocol) lets an AI tool such as Claude Code or Codex read data from other services. With the CrawlCoach MCP server, your agent reads your missing pages, fixes the template or setting behind them in your project, and asks CrawlCoach to recheck them. It works with Claude Code, Codex, Claude, VS Code with GitHub Copilot, and Zed.
Start here
- Get started: create an account, connect Search Console, and check your first site.
- Connect an AI agent: add the CrawlCoach MCP server to your agent and sign in.
- MCP tools reference: every tool, its inputs, and what it returns.
- HTTP API reference: the
/mcpendpoint, authentication, errors, and rate limits. - Plans and limits: what each plan includes, and the limits on each tool.
Machine-readable files
- Docs index for AI agents: every docs page, with a link to its Markdown copy.
- OpenAPI description: the HTTP endpoints, in OpenAPI 3.1.
- Site summary for AI assistants: CrawlCoach's plans and its indexing guides.
Every docs page has a Markdown copy. Add .md to the page's URL, or send the request with an Accept: text/markdown header.