Agentaeo Mcp Server
io.github.digitaldatadrivenPublished by GitHub account digitaldatadrivenv0.1.8Updated Oct 24, 2026
AEO audit tool — measure brand visibility across ChatGPT, Perplexity, Claude, and Google AI.
Overview
A local MCP server that runs AI citation audits, showing which brands ChatGPT, Perplexity, Claude and Google AI cite for buyer queries and why.
- What you can do
- Run citation audits for a domain across buyer queries on four AI engines, with citation rates per engine and per query and the competitor winning each query. Estimate monthly revenue leakage and the structural reasons AI skips a brand. Produce a prioritised 30-day fix plan, copy-paste JSON-LD schema and an llms.txt file. Compare several domains by Retrieval Marketing Score and citation gap, and generate an executive summary for stakeholders.
- When to use it
- Use it when you want to know why AI assistants recommend competitors instead of your brand, or when running AEO/GEO research for your own site or client domains and turning the findings into concrete fixes.
- Requirements
- Runs as a local process on the desktop via npx from the npm package @agentaeo/mcp-server; no authentication, environment variables or headers are declared. Network access is implied because audits query live AI engines.
Installation
In SourceWeft
- Open Agentaeo Mcp Server in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
AgentAEO MCP Server
[npm version] [Anthropic MCP Registry] [Glama AAA] [License: MIT]
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.
Install in 2 minutes
Then 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.
What this measures
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
Why this exists
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.
How AgentAEO differs from other AEO tools
Three workflows to try now
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?"
Run a complete AEO audit and fix plan in 30 minutes
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
Built on the Retrieval Marketing Framework™
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
Source: README.md at commit b039b5a
Tools
0Version history
1- v0.1.8LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts