Check what Perplexity, Claude, ChatGPT, Gemini, and Google AI Overviews cite for any query.
Check what Perplexity, Claude, ChatGPT, Gemini, and Google AI Overviews cite for any query.
An MCP server for agents and developers who need to know which URLs get cited by AI search engines for any query. Install once, query from any MCP-compatible client (Claude Desktop, Cursor, Claude Code, Continue, Cline, n8n, LangGraph). Self-hosted, no account, no centralized backend. Bring your own API keys; nothing is stored on a remote server.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| audit_citation_readiness | url) - chains citations_predict + audit_schema |
| audit_competitor_snapshot | query, your_url?) - chains competitors_canonical_set + competitors_compete |
| audit_crawler_checkup | url) - runs audit_crawler_access and writes a remediation list |
| audit_gap_analysis | domain, days?) - drives signals_gsc_gap and suggests next moves |
| audit_sitemap_coverage | sitemap_url) - runs audit_sitemap_map and recommends priorities |
| citation | //domain/{domain}/cited-for - dynamic template: citations for {domain} |
| citations_provenance | Recommended first tool. Fan a query across engines; per-URL cross-engine consensus matrix. Returns interpretation_note per engine. |
| citations_check | URLs cited by Perplexity / Claude / ChatGPT / Gemini / Google AI Mode for a query; or web rank via bing_serp / brave_serp |
| citations_evidence | Extract the cited snippet from raw_answer for each citation (why, not just that) |
| citations_predict | Citation likelihood from public signals - no LLM fired |
| citations_trend | Time-series report of citation rate + per-query gained/lost deltas |
| citations_freshness | Recency score (halflife=365d) for the pages an engine cites |
| domain_am_i_cited | Domain citation check. With engine=auto (default): fans across all available LLM engines, returns per-engine breakdown + cross-engine consensus. Pin engine= to |
| domain_cited_for | Queries the domain has been cited for, from local cache |
| domain_cited_for_diff | Diff of domain_cited_for between two time windows for a domain |
| signals_ai_overview | Google AI Overview presence + cited sources |
| signals_wikipedia | List Wikipedia articles referencing a domain (zero keys) |
| signals_gsc_gap | Join Google Search Console performance with AI citation status |
| signals_answer_box | Bin each citation's first mention in raw_answer into early/middle/late thirds |
| panel_track | Save / load / list named query panels (editorial watchlists) |
| panel_run | Run a panel through domain_am_i_cited and snapshot to disk |
| report_visibility | One-call AI visibility report over a query set (or panel): citation rate (mention frequency), share of voice vs competitors, average rank, and brand sentiment. |
| competitors_canonical_set | Top cited domains per query, aggregated across engines |
| competitors_compete | End-to-end competitive snapshot: your URL vs top cited competitors |
| competitors_compare | Side-by-side citations_predict across 2-10 URLs |
| audit_schema | Deep schema.org validation - required fields per @type, malformed JSON-LD |
| audit_structured_data | Repair-oriented schema.org diagnostics + suggested patches |
| audit_crawler_access | Verify GPTBot / ClaudeBot / PerplexityBot / CCBot / Google-Extended etc. can fetch a URL |
| audit_sitemap | Bulk citations_predict across every URL in a sitemap, worst-first |
| audit_sitemap_map | Cross-reference sitemap URLs with cached citations (inverse of audit_sitemap) |
| audit_llms_txt | Generate an llms.txt (https://llmstxt.org) from a sitemap |
{
"mcpServers": {
"citation-intelligence": {
"command": "npx",
"args": [
"-y",
"@automatelab/citation-intelligence"
],
"env": {
"PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY",
"SERPAPI_KEY": "YOUR_SERPAPI_KEY",
"ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY",
"OPENAI_API_KEY": "YOUR_OPENAI_API_KEY",
"GEMINI_API_KEY": "YOUR_GEMINI_API_KEY"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| PERPLEXITY_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
| SERPAPI_KEY | Declared in the maintainer’s client configuration. | Check documentation |
| ANTHROPIC_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
| OPENAI_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
| GEMINI_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
A Model Context Protocol server that provides browser automation capabilities using Puppeteer. This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real…
A Model Context Protocol (MCP) server for the DataForSEO API, enabling modular and extensible integration of DataForSEO endpoints with support for
Proofite turns the sources you choose — newsletters, RSS feeds, monitored web searches, saved links — into one personal briefing every morning, written by AI and available as a podcast. This MCP…
Screenshot any web page, or read it as clean Markdown, with consent banners, ads and popups removed.