AI Visibility MCP for Cursor

In Cursor, the raw answers the six engines actually give are one chat message away: ask, and fetch_raw_answers returns the answer text plus every cited source as a tool result. One MCP server, one deliberately narrow tool - and the evidence lands beside the exact files that need editing, so the check and the fix happen in the same window.

Connect AgentGEO to Cursor

Cursor configures MCP servers in JSON. Add an agentgeo entry to ~/.cursor/mcp.json for every project, or to .cursor/mcp.json in a repo so the whole team gets the tool when they open it:

{
  "mcpServers": {
    "agentgeo": {
      "command": "npx",
      "args": ["-y", "agentgeo-mcp", "--key", "ag_live_..."]
    }
  }
}

The server is a zero-dependency npm package that speaks MCP over stdio (Node.js 18+). A live ag_live_ key comes with a plan. Testing the wiring first? An ag_test_ key always returns clearly labelled demo records at zero credits. Reload, and fetch_raw_answers appears in Cursor's available tools.

Each call returns one record per surface - the provider's answer, verbatim, with every source it cited as structured data (the full record also carries the raw providerFields):

{
  "surfaceKey": "perplexity",
  "status": "delivered",
  "answerText": "...",
  "sources": [
    { "title": "...", "url": "https://...", "position": 1 }
  ],
  "fetchedAt": "2026-07-13T09:12:04Z",
  "latencyMs": 8412,
  "providerRecordId": "..."
}

What to ask once it's connected

No arguments to memorize - describe the check in chat and Cursor shapes the call. Say "in France" and it passes country through (it defaults to US). Worth knowing: language only reaches Google AI Overviews, where it drives the search locale - the chatbot surfaces take a country and no language field. Asks that do real GEO work with your files open:

• "Fetch what ChatGPT and Perplexity answer for 'best headless CMS for marketers' and list which domains each cites."
• "Run our homepage's target query across all six surfaces and tell me whether ourdomain.com shows up in any citation list - and at what position."
• "Pull Gemini's answer for our category. If our landing page isn't cited, open app/(marketing)/page.tsx and tighten the opening so it answers the query directly."
• "Diff the citation sets between google_ai_overview and google_ai_mode for 'best analytics for startups' and summarize what AI Mode surfaces that Overviews doesn't."
• "Fetch Copilot's answer for 'alternatives to Segment' - are we in the answer text, or only in the sources?"
• "Re-fetch last week's query and diff sources[] against the record saved in geo-notes.md, then edit the docs page that lost its citation."

What the MCP server gives you

Deliberately thin - an answer-access layer for your agent, not an analytics product bolted into your IDE.

• One narrow tool - fetch_raw_answers posts to AgentGEO's API and returns the run envelope verbatim. Nothing else to learn, nothing else to break.
• Six engines behind one contract - ChatGPT, Perplexity, Gemini, Google AI Overviews, Google AI Mode and Copilot with an identical record shape, so widening a check is one more word in the ask.
• Structured sources[] - every citation with its title, URL and position, ready for the agent to diff, count or grep against your domain. No links regexed out of prose.
• Raw records only - no rankings, sentiment or visibility scores. The conclusions come from Cursor, which has your repo, your competitors and your history in context.
• Managed-scraper engine, maintained for you - under the hood the server talks to POST https://api.agentgeo.org/v1/fetches; keeping six collection paths healthy is AgentGEO's job, not a headless browser in your project.
• Usage-based billing - one credit per run, failed runs cost zero, priced by usage rather than per seat.

What it doesn't do

The narrowness is the point. Cursor holds your repo, your positioning and your judgment; conclusions computed outside that context would be worth less than raw records analyzed inside it - that is the whole GEO data layer argument. So, honestly:

• No dashboards. Records arrive as tool results; the report is whatever Cursor writes from them, committed in your repo.
• No visibility scores or sentiment. Raw answerText and sources[] only - the judgment layer is deliberately left to your agent.
• No recommendations engine. Cursor drafts fixes against your actual pages, which beats generic advice every time.
• Not instant. Requests wait up to 180 seconds - live surfaces are slow. An AI Overview SERP round-trip runs 40-90s, and some chatbot scrapes exceed the sync budget entirely: those records come back failed with a providerFields.snapshot_id, and a follow-up call with that id and the same single surface redeems the finished answer without paying for a re-scrape (not valid for google_ai_overview).

Prefer the REST API?

The MCP server is a thin wrapper over the same endpoint your code can hit directly: POST https://api.agentgeo.org/v1/fetches. Script the sweep in Python or curl and you get the identical contract - same surfaces, same records, same credits - so a check born in a Cursor chat can graduate to CI unchanged.

Who builds on this

Product engineers and content-minded developers who work the marketing site and docs in Cursor. When the pages you'd fix are already in the file tree, having your agent fetch how the six engines answer for your category - and edit the page that's missing from the citations - beats alt-tabbing to a separate dashboard. A committed .cursor/mcp.json gives the whole team the tool the moment they open the repo. See where you stand first with the free audit, or see how the approaches compare.