AEO Copilot is an AEO tool with a native MCP server, included on the $9/month Startup plan. Connecting it to Claude Code takes 2 steps: create an API key in Settings, then run 1 claude mcp add command. From there Claude can read your visibility scores, results, and recommendations, and even run prompts, inside the conversation.
Most AI visibility tools give you a dashboard. You log in, check the numbers, log out. Fine for reporting. Less useful when you want to do something about what you find.
Connecting AEO Copilot to Claude changes that. Instead of opening a dashboard, you ask a question: which prompts mention my competitors but not me? What's my visibility trend this month? What should I fix first? Claude pulls the data and answers directly.
Which AEO tools have an MCP server?
I built AEO Copilot, so weigh my take on it accordingly. Competitor prices were checked on their pricing pages on 29 September 2026.
Most of the established platforms now do, but the price gap between them is wide. As of September 2026, here is where the market stands among the tools with a public pricing page and a verifiable MCP integration (full, dated pricing table):
If your team already works with agents, that last column is the one that matters. Rankshift's MCP starts at $92/month, Peec's at €85, Otterly's at $189, Scrunch's at $300, and Profound's needs an Enterprise contract. AEO Copilot includes it at $9, and its MCP includes write actions (create brands, add prompts, run tracking), where Peec's was read-only at launch.
A wave of smaller, newer AEO tools has also started shipping MCP servers or agent-facing APIs over the past few months. "Your agent can run this itself" is quickly becoming an expected feature in this category, not something only 1 tool offers. What still sets AEO Copilot apart is that the server is native (not a third-party wrapper), fully open source and auditable on GitHub, covers all 4 major LLMs (ChatGPT, Claude, Perplexity, Google AI Overview) rather than a subset, and ships on the cheapest paid plan instead of being gated to an enterprise tier.
This is how to connect it. Short on time? Point your agent at aeo-copilot.com/connect.md and ask it to set up the connection. The file is written for agents, so yours can handle the install on its own.
The API
26 endpoints in total: reads, writes, prompt management, runs, and technical scans. Most integrations start with these 5 GET requests, all returning JSON.
Authentication is a Bearer token. Every request needs this header:
Getting your API key
!Where to create an API key in AEO Copilot: Settings, API tab, name your key, Create
Four clicks, numbered in the screenshot:
- Open Settings with the gear icon in the top-right corner
- Pick the API tab
- Give the key a name you'll recognize later, like "Claude Code" or "Dashboard Integration"
- Hit Create and copy the key
It starts with aeo_. You only see the full key once at creation, so store it right away. Keys don't expire, but you can revoke any of them from the same tab. The page also shows a quick reference with ready-to-copy curl commands.
A basic request
Grab the brand id from the response and use it with the other endpoints.
Filtering results
The /results endpoint takes optional query parameters:
from and to take ISO dates. limit defaults to 100, max 500. topicId filters to a single topic.
The MCP server
MCP is the protocol that lets AI assistants connect to external tools. The AEO Copilot MCP server wraps the API so you can ask Claude about your brand's visibility data without leaving the conversation.
!How your AI agent talks to AEO Copilot: the agent calls the MCP server running on your machine, the MCP server calls the REST API with your key, and the API reads your brand's tracking data across ChatGPT, Claude, Perplexity, and Google AI Overview
The server is open source: github.com/sofianbettayeb/aeo-copilot-mcp
The install commands for Claude Code and Claude Desktop are below. For Codex, Cursor, or OpenCode, or if you just want your agent to do it, hand it aeo-copilot.com/connect.md. It carries the config for each of the 4 agents plus a verification step.
Install in Claude Code
Install in Claude Desktop
Edit claude_desktop_config.json:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
%APPDATA%\Claude\claude_desktop_config.json
Restart Claude Desktop after saving.
What it looks like in practice
Once connected, you talk to Claude like you would any conversation:
- "What's my brand's AI visibility score?"
- "Which prompts mention my competitors but not me?"
- "Show me my visibility trend for the last 30 days"
- "What should I fix to improve my AI visibility?"
- "How does my brand compare to [competitor] in AI-generated answers?"
Claude calls the API and translates the response into plain language. You can follow up, filter by date, drill into a specific topic. It works the way you'd expect a conversation to work.
This is how users on the Startup plan run it day to day:
> It checks every week whether our Shopify apps come up in the answers. I never open it, I just ask Claude and it does the work.
> Kostas Zhukov, videopoint.ai
What's coming
The MCP server now covers writes too: create a brand, add topics and prompts, edit existing prompts one at a time or in bulk, run them across all four LLMs, and run the technical scan. That means you can build a full client report from a single Claude Code conversation, which is the workflow in Build an AI visibility report for a client in minutes. Next on the roadmap: webhooks and pushing results into external tools.
If you build something on top of it, or hit something that doesn't work as expected, open an issue on GitHub: github.com/sofianbettayeb/aeo-copilot-mcp.
Frequently asked questions
Which AEO tool has an MCP server?
As of September 2026: AEO Copilot (native, open source, from $9/month), Rankshift (from $92/month), Otterly.ai (from $189/month), Peec.ai (launched April 2026, all paid plans from €85/month, read-only at launch), Scrunch AI (launched May 2026, all plans from $300/month) and Profound (launched October 2025, Enterprise only in practice). A growing number of newer, smaller AEO tools advertise MCP or agent-facing API access too. AEO Copilot is the cheapest way to get MCP, from $9/month, and its server includes write actions: create brands, add prompts, run tracking. See the comparison table above for the full breakdown.
Is there an AI visibility tool that works with Claude Code over MCP?
Yes. AEO Copilot ships an open-source MCP server. Add it to Claude Code with the one claude mcp add command above, and Claude can read your brand's visibility, results, and recommendations directly.
How do I check my brand's ChatGPT visibility from inside Claude Code?
Once the server is connected, ask in plain language: "What's my brand's AI visibility score?" or "Which prompts mention my competitors but not me?" Claude calls the API and answers in the conversation. No dashboard, no export.
Can I plug it into my own AI agent workflow?
Yes. Everything the MCP exposes is also a REST API, so you can wire AEO Copilot into any agent stack or automation, not just Claude. Give your agent the URL aeo-copilot.com/connect.md and it can set up the connection itself. API and MCP access is included from the Startup plan at $9/month.
Get your API key →