AI Rank Lab tools, inside your AI agent
The AI Rank Lab MCP server exposes the same tools as the developer API — the full SEO + AEO + GEO checker, live Google Search, AI Overview and AI Mode lookups for any country and device, keyword research, Core Web Vitals, AI brand-visibility checks, FAQ and llms.txt generation, plus your Google Analytics 4, Search Console, bot-visit and citation data — over the Model Context Protocol. Add it to Claude Code, Claude Desktop, or Cursor and your agent can run them directly.
Introduction
The Model Context Protocol (MCP) is an open standard that lets AI assistants call external tools. Our MCP server is a thin layer over the /api/v1 REST API: same tools, same credit billing, same account — but callable by Claude, Cursor, or any other MCP-compatible client as part of a conversation.
The server uses the Streamable HTTP transport in stateless mode, so there is nothing to install or host — you point your client at the endpoint with your API credentials.
Endpoint & authentication
The server lives at a single endpoint:
POST https://www.airanklab.com/api/v1/mcpEvery request must carry the same two headers as the REST API: x-api-key and x-api-secret. Generate both from Dashboard → API & Integrations.
Your MCP client config stores the secret in plain text on your machine. Keep the config file out of version control, and rotate the key pair from the dashboard if it ever leaks.
Claude.ai (Web App)
To connect the MCP server directly in the Claude.ai web interface, open the Add custom connector dialog. Claude.ai does not support custom headers, so your credentials go in the URL query string instead.
Paste the following URL into the Remote MCP server URL field, replacing the placeholders with your actual API key and secret. Leave the Advanced OAuth fields blank.
https://www.airanklab.com/api/v1/mcp?x-api-key=YOUR_API_KEY&x-api-secret=YOUR_API_SECRETBecause Claude.ai does not support custom headers, you must include your credentials in the URL query parameters. Be aware that this may cause them to appear in our server access logs.
Use the URL exactly as shown — the www. host and no /sse suffix. Claude.ai connects over Streamable HTTP and posts to the exact URL you paste; a different host or path returns an error, and Claude then falls back to an OAuth sign-in flow that this server does not offer.
Claude Code
One command adds the server to Claude Code (CLI v1.x or later):
claude mcp add --transport http airanklab https://www.airanklab.com/api/v1/mcp \
--header "x-api-key: YOUR_API_KEY" \
--header "x-api-secret: YOUR_API_SECRET"Then ask Claude Code things like “run the SEO + AEO + GEO check on example.com and summarize the critical issues” or “who does Google's AI Overview cite for ‘best CRM for startups’ in India on mobile?” — it will call the seo-aeo-geo-audit and google-ai-overview tools for you.
Claude Desktop
Add this to your Claude Desktop configuration (Settings → Developer → Edit Config, file claude_desktop_config.json), then restart the app:
{
"mcpServers": {
"airanklab": {
"url": "https://www.airanklab.com/api/v1/mcp",
"headers": {
"x-api-key": "YOUR_API_KEY",
"x-api-secret": "YOUR_API_SECRET"
}
}
}
}Cursor
Add the same block to ~/.cursor/mcp.json (global) or .cursor/mcp.json in your project:
{
"mcpServers": {
"airanklab": {
"url": "https://www.airanklab.com/api/v1/mcp",
"headers": {
"x-api-key": "YOUR_API_KEY",
"x-api-secret": "YOUR_API_SECRET"
}
}
}
}Available tools & pricing
MCP tools mirror the REST tool endpoints one-to-one and spend the same credit balance — a tool costs the same whether you call it from the dashboard, the REST API, or MCP. Data reads are free; failed tool calls are refunded automatically.
The three Google tools (google-search, google-ai-overview, google-ai-mode) take a country and a device— name the country (“India”), its ISO code (“IN”) or its numeric location code (2356), and pick desktop or mobile. Results differ markedly between the two, so measure the one your buyers actually use. The search-locations tool lists every supported market. The GA4 and Search Console tools are free because they read your own Google data — connect those accounts in the dashboard first.
ai-citation-check asks ChatGPT, Perplexity, Claude and Gemini the same question in one call and reports which of them cite you — it is billed per engine, so naming fewer engines costs less. The backlink tools (backlinks-overview, backlinks-history, backlinks-list, referring-domains, anchor-text, bulk-domain-authority) work on anydomain, not just the ones registered on your account, so an agent can research a competitor’s link profile directly. The free backlink-filters tool lists the presets, modes and fields the filtered backlink queries accept.
| Tool | Description | Credits per call |
|---|---|---|
ai-citation-check | Ask ChatGPT, Perplexity, Claude and Gemini one question and see who cites you | 100 per engine |
backlinks-list | Every individual backlink, with anchors, authority and spam signals | 150 |
seo-aeo-geo-audit | Full SEO + AEO + GEO checker — the same three-pillar report as the dashboard | 50 |
audits | Technical + AEO audit of a single URL | 50 |
google-search | Live Google SERP for one query, by country and device | 100 |
google-ai-overview | Google's AI Overview answer and the sources it cites | 100 |
google-ai-mode | Google's AI Mode conversational answer and its sources | 100 |
brand-visibility | Ask a live AI engine about a brand | 100 per engine |
keyword-research | Keyword volume, difficulty, intent and live SERP | 50 typical; billed per lookup |
core-web-vitals | Core Web Vitals / PageSpeed scan | 25 |
referring-domains | Domains linking to any site, ranked by authority | 25 |
anchor-text | Anchor text distribution and over-optimization signals | 25 |
bulk-domain-authority | Authority rank for up to 100 domains in one call | 25 |
faq-generator | Generate an FAQ plus FAQPage schema for a page | 20 |
llms-txt | Generate an llms.txt manifest | 20 |
backlinks-overview | Backlink profile summary for any domain: rank, referring domains, spam score | 15 |
backlinks-history | Month-by-month backlink trend with new and lost links | 15 |
backlink-filters | Filter presets, modes and fields the backlink tools accept | Free |
gsc-performance | Search Console clicks, impressions, CTR and position | Free |
gsc-sites | Your verified Search Console properties | Free |
ga4-report | Any GA4 metrics and dimensions over your property | Free |
ga4-realtime | GA4 activity in the last 30 minutes | Free |
ga4-properties | Your connected GA4 properties | Free |
tracking-stats | AI bot visit stats for your domain | Free |
citations | Where AI engines cite your site | Free |
search-locations | Countries, languages and devices the search tools accept | Free |
keyword-research-estimate | Preview a keyword-research cost before running it | Free |
credits | Current credit balance | Free |
Long-running tools
Heavier tools (audits, brand visibility) normally finish within the request. Each call has a 120-second budget: if the work isn't done in time, the tool returns a jobId with polling instructions instead of the result.
Poll GET /api/v1/jobs/{jobId} (REST, same headers) until the status is completed — see Async jobs in the API reference.
Rate limits
MCP requests count against the same per-key limit as the REST API: 60 requests per minute by default. A 429 response includes Retry-After. Need a higher limit? Contact us.
Connect your agent
Generate your API key and secret, paste one config block, and your AI agent can run real marketing tools.
Get your API key