Citerank MCP Server:
AI Visibility Checks, Called Directly From Your Agent
Give Claude Code, Cursor, and Claude Desktop direct access to Citerank's AI citation audits, schema generation, and agentic readiness checks. Five tools, one MCP server - no browser tab, no copy-pasting URLs, no leaving your agent's context.
Your Agent Is Already Shipping Pages. Now It Can Check Them.
If you're building a page with Claude Code or Cursor, the natural checkpoint before you ship is: will AI engines actually cite this? Today that means stopping, opening a browser, running an audit somewhere else, and copying the findings back into your agent's context by hand.
The Citerank MCP server removes that round trip. It exposes five of Citerank's core tools directly to any MCP-compatible agent, so a citation audit, a schema generation pass, or an agentic-readiness check becomes a single tool call inside the same session where the page is being built.
Five Tools, Callable by Any MCP Client
-
citerank_analyze_url
Runs a full AI visibility audit on a URL. Returns schema analysis, AI citation score, E-E-A-T signals, agentic readiness, and prioritized issues. Accepts an optional focus: full, schema, citations, agentic, or eeat.
-
citerank_check_brand_citations
Checks whether a brand or domain is cited in AI-generated answers across Google AI Overviews and Gemini. Returns citation rate, share of voice, top cited queries, and competitor comparison for up to 10 keywords.
-
citerank_generate_schema
Analyzes a page and produces ready-to-implement JSON-LD structured data. Schema type is auto-detected from page content, or can be specified directly.
-
citerank_check_agentic_readiness
Tests whether a site is ready for AI agent interactions: MCP endpoint, WebMCP declarative tools, potentialAction schema, A2A agent card, and llms.txt.
-
citerank_simulate_agent_journey
Simulates an AI agent attempting to complete a task - book, quote, contact, buy, or subscribe - on a website, and returns the exact step where it fails along with the fix.
Works With the Agents You Already Use
-
Claude Code
Add the Citerank MCP server through Claude Code's MCP settings using the connection details on the setup page. Tools appear in-session immediately.
-
Claude Desktop & other MCP clients
Any client that speaks Model Context Protocol can connect the same way - no Citerank-specific SDK required.
-
Cursor
Add the server in Cursor's MCP configuration and save - the five Citerank tools appear in your agent's tool list.
Frequently Asked Questions
- What is the Citerank MCP server?
- A Model Context Protocol server that exposes five AI visibility tools directly to AI coding agents - Claude Code, Cursor, Claude Desktop, and any other MCP-compatible client. Instead of switching to a browser to check whether a page is cited by AI or has valid schema, an agent can call citerank_analyze_url or citerank_check_brand_citations mid-task and get structured results back.
- What tools does it expose?
- Five: citerank_analyze_url, citerank_check_brand_citations, citerank_generate_schema, citerank_check_agentic_readiness, and citerank_simulate_agent_journey. Full parameters for each are on the setup page.
- How do I connect it to Claude Code?
- Add the Citerank MCP server the same way you'd add any other MCP server in Claude Code's settings, using the connection details on the setup page. Once connected, the five tools appear in Claude Code's tool list and can be called mid-session.
- Is it free?
- Yes. Connecting the MCP server and calling its tools is free, with the same usage limits as the free web tools. Paid plans add higher call volume, saved history across calls, and access to the full Citerank dashboard for the same audits run through the API.