The @agentaeo/mcp-server enables running Answer Engine Optimization (AEO) audits and generating AI-optimized content suites for websites, measuring and improving visibility across AI-powered search engines like ChatGPT, Perplexity, Claude, and Google AI.
Core capabilities:
Run AEO Audits (run_aeo_audit): Start an async AEO audit for any URL, with a free tier (8 queries) or paid tier (40 queries), and an optional primary keyword.
Check Audit Status (check_aeo_audit_status): Poll a running audit by auditId — free tier audits stop at a preview, paid audits deliver a full report.
Generate AEO Content Suite (generate_aeo_content_suite): Kick off async generation of a full content bundle (HTML, JSON-LD structured data, and llms.txt) from a completed audit. Supports admin bypass mode for internal QA.
Check Content Suite Status (check_aeo_content_suite_status): Poll content suite generation progress by orderId until completed or failed (typically 5–25+ minutes).
Download Content Suite ZIP (download_aeo_content_suite_zip): Download the completed content suite as a ZIP file to a specified directory or the current working directory.
Allows running and monitoring Answer Engine Optimization (AEO) audits and generating optimized content suites to analyze and improve content visibility within Google AI.
Allows running and monitoring Answer Engine Optimization (AEO) audits and generating optimized content suites to analyze and improve content visibility within Perplexity's AI search results.
Ask Claude: "Why is [competitor] being cited instead of us for [category] queries?" Get the answer. Get the fix.
AgentAEO is a retrieval intelligence layer for AI agents. It tells Claude, Cursor, and any MCP-compatible agent which brands are winning AI citations and exactly why.
npx @agentaeo/mcp-server@latestThen in Claude Desktop, ask:
"Run an AI citation audit on [domain.com] for [category] queries. Tell me which competitors are being cited instead and why."
That is it. You now have live selection intelligence inside your AI workflow.
Related MCP server: Citare
AgentAEO runs real buyer queries across ChatGPT, Perplexity, Claude, and Google AI and returns:
Citation rates per engine per query
Which competitor wins each query
Revenue leakage estimate ($/month)
Exact structural reasons AI skips you
Copy-paste schema fixes
60% of brands investing in SEO are invisible in AI-generated answers despite strong Google rankings.
This is the Selection Gap: AI finds your brand but does not consistently choose it. Competitors enter the consideration set before you do.
AgentAEO measures this gap. Quantifies it in dollars. Generates the fix.
Also known as: Generative Engine Optimization (GEO), Answer Engine Optimization (AEO), AI SEO — AgentAEO measures the citation layer that determines whether AI recommends you or your competitor.
Capability | AgentAEO | Conductor | Profound | AthenaHQ | seoClarity |
Live citation testing across 4 engines | ✅ | ❌ | ❌ | ❌ | ❌ |
Revenue-at-risk estimate | ✅ | ❌ | ❌ | ❌ | ❌ |
30-day fix blueprint | ✅ | ❌ | ❌ | ❌ | ❌ |
Deploy-ready JSON-LD schema | ✅ | ❌ | ❌ | Partial | ❌ |
llms.txt generation | ✅ | ❌ | ❌ | ❌ | ❌ |
Free tier | ✅ | ❌ | ❌ | ❌ | ❌ |
One-time diagnostic (no subscription) | ✅ | ❌ | ❌ | ❌ | ❌ |
MCP server on Anthropic registry | ✅ | ✅ | ✅ | ❌ | ✅ |
1. Competitive intelligence
"Audit stripe.com for payment processing queries. Which fintech brands are being recommended instead of Stripe by ChatGPT and Perplexity?"
2. Own brand monitoring
"Run a citation health check on [your-domain.com] and give me the monthly revenue leakage estimate plus the top 3 fixes."
3. Agency research
"Audit these 5 domains: [list]. Rank them by Retrieval Marketing Score. Which has the biggest citation gap versus its competitors?"
With AgentAEO MCP inside Claude Desktop or Claude Cowork, what used to take 30 days of manual AEO work runs in 30 minutes:
Ask Claude:
"Run a complete AEO audit on [domain.com]. Test buyer queries across all 4 engines, identify citation gaps, generate the 30-day fix blueprint, create the JSON-LD schema files, write the llms.txt, and give me a board-level summary of revenue at risk."
Output in one session:
Citation grade per engine per query
Revenue leakage estimate
Prioritised 30-day fix plan
Copy-paste JSON-LD (FAQPage, HowTo, Organization)
llms.txt file ready to publish
Executive summary for stakeholders
The only AEO platform with a working MCP server on the official Anthropic registry. AAA rated on Glama.
→ agentaeo.com
→ retrieval.marketing
→ @agentaeo/mcp-server on npm
Check status of an AEO audit. Poll until free_preview_ready (free) or is_complete at full report (paid). If paid_pipeline_pending is true, keep polling.
Inputs: auditId (required).
Poll Content Suite generation. After generate_aeo_content_suite returns (HTTP 202), call every 15–30s until status is completed or failed. Same X-API-Key as generate.
Inputs: orderId (required).
Download the Content Suite ZIP after status is completed (same AGENTAEO_API_KEY as generate). Saves to cwd or AGENTAEO_MCP_DOWNLOAD_DIR.
Inputs: orderId (required), outputFileName.
Start Content Suite generation (HTML + JSON-LD + llms.txt) for a completed audit — async (returns in seconds with orderId). Poll check_aeo_content_suite_status every 15–30s until completed (often 5–25+ min). Uses AGENTAEO_API_KEY — no shell/curl. Admin QA without Cashfree: adminContentBypass=true + allowlisted key. Otherwise pass orderId after payment.
Inputs: auditId (required), packageType, orderId, adminContentBypass.
Start an AEO audit for a URL (async). Returns auditId immediately. Then call check_aeo_audit_status every 10–15s until is_complete or free_preview_ready (free tier stops at step 2).
Inputs: url (required), keyword, tier.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Scored across 5 tools
Each tool has a distinct, non-overlapping purpose: run_aeo_audit initiates an audit, check_aeo_audit_status monitors it, generate_aeo_content_suite starts content generation, check_aeo_content_suite_status monitors that, and download_aeo_content_suite_zip retrieves the result. The descriptions clearly differentiate these workflows, leaving no ambiguity for an agent to misselect tools.
All tool names follow a consistent snake_case pattern with clear verb_noun structure (e.g., run_aeo_audit, check_aeo_audit_status, generate_aeo_content_suite). The naming is predictable and uniform across all five tools, making them easily readable and systematic.
With 5 tools, this server is well-scoped for managing AEO audits and content suites. Each tool serves a specific role in the workflow, from initiation to monitoring to download, and none appear redundant or unnecessary, fitting the domain appropriately without being too sparse or bloated.
The tool set provides complete coverage for the AEO audit and content suite lifecycle: it includes tools to start audits (run_aeo_audit), monitor their status (check_aeo_audit_status), generate content (generate_aeo_content_suite), monitor that generation (check_aeo_content_suite_status), and download results (download_aeo_content_suite_zip). There are no obvious gaps, enabling agents to handle the entire process from start to finish.
Audit your brand's visibility across ChatGPT, Gemini, Claude, Perplexity + 6 more engines.
Diagnose brand visibility in AI answers (ChatGPT, Perplexity, AI Overviews). Free + paid audits.
Track your brand's visibility in AI search across Claude, ChatGPT, Perplexity, and Gemini.
Free AI visibility and GEO audit: see what AI reads on your site and whether its answers cite you.
