Features / MCP server

Ask your AI assistant
about your GEO data.

llemmy ships a Model Context Protocol server, so Claude, Cursor or any MCP client can read your projects, prompts, AI responses, brand visibility and citations, and answer questions about them in plain language. Read-only and scoped to your API key. No other GEO platform offers this.

Read-only · Scoped by API key · Works with Claude, Cursor and any MCP client
Prefer to stay in the dashboard? The same plain-language chat is built right into llemmy. meet Ask llemmy →
Claude · connected to llemmy
MCP server · read-only · scoped to your API key
5 tools available
How is Northwind Coffee's AI visibility trending this month, and who's beating us?
brand_stats top_citations

Here's the snapshot llemmy returned for Northwind Coffee:

Answers scanned
500
last 30 days
Prompts tracked
24
across 7 engines
Cited domains
37
seriouseats.com leads

Your nearest rival leads on Perplexity, where they're cited first in 4 of 10 buying-intent answers. Want me to pull the prompts where they out-rank you?

Your GEO data, where you already work.

The Model Context Protocol is the open standard for letting an AI assistant read live data from a tool. Connect llemmy once, then ask about your AI visibility from inside Claude or Cursor. No dashboard tab, no export, no SQL.

💬
Ask in plain language

"Ask your AI assistant how your brand's visibility is trending." Your assistant calls the right llemmy tools and answers, with no query language to learn.

🔒
Read-only & secure

The server can only read. It's scoped to your API key, so an assistant sees exactly your data and nothing else, and can never change a thing.

No competitor has this

A flagship developer and agency differentiator: llemmy is the GEO platform you can talk to from your own AI assistant.

Get started in minutes

Connect llemmy as an MCP server.

1
Create an API key

In llemmy, open API Keys and generate one. It scopes the MCP server to your data.

2
Add the server to your client

Point Claude, Cursor or any MCP client at the llemmy server and paste your key. One config block, shown opposite.

3
Ask in plain language

"How is my brand's visibility trending?" "Which sources does AI cite most?" Your assistant does the rest.

Example client config
{
  "mcpServers": {
    "llemmy": {
      "url": "https://llemmy.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
Then just ask
"How is Northwind Coffee's AI visibility trending this month?"
"Which sources do AI engines cite most for us?"
"Summarize the latest responses for my buying-intent prompts."
The toolbox

Five read-only tools your assistant can call

Your AI client picks the right tool for the question and stitches the results into an answer. Every one is read-only.

list_projects
Your projects

Lists every project in your workspace, the starting point for any question about a specific brand.

list_prompts
Tracked prompts

Returns the prompts llemmy runs against the engines for a project, the questions you're tracking your brand against.

list_responses
AI responses

Pulls the actual answers each engine gave, so your assistant can read, quote and summarize what ChatGPT, Claude, Gemini and the rest said.

brand_stats
Brand visibility

Returns visibility and mention metrics for a brand across the engines, the numbers behind "how am I trending?"

top_citations
Top cited sources

Surfaces the pages AI engines cite most when they answer about you, the sources to win, audit or reclaim.

Read-only by design

Safe to connect. Scoped to you.

Giving an AI assistant access to a tool should never mean giving it the keys. llemmy's MCP server can only read. It cannot run prompts, change settings, delete data or touch billing. And because it authenticates with your API key, it is scoped to your account and the projects you can access, and never reaches another tenant's workspace.

No write access - the tools list, fetch and summarize; they never mutate
Account scoped - same workspace isolation as the rest of llemmy
Revoke anytime - delete the key in API Keys and access is gone
What the MCP server can and can't do
Read projects, prompts and AI responses
Read brand visibility and top citations
See only the workspace your key unlocks
Run prompts or trigger refreshes
Edit settings, delete data or change billing
Reach any other tenant's data
Built for builders and agencies

Where the MCP server earns its keep

Developers

Pull GEO data into Cursor or Claude without leaving your editor. Ask for the numbers as you build the report, dashboard or content brief.

Agencies

Ask your assistant to summarize visibility across every client project at once, then turn the answer into a client-ready update in seconds.

Analysts

Interrogate the AI responses themselves: quote the exact passages, find the cited sources, and explore patterns conversationally.

Keep exploring
Teams & multi-seat
Invite your team and clients →

Add teammates, plus free read-only viewer seats so every client can watch their own brand.

Visibility tracking
How often AI names you →

One visibility score across every engine, the data the MCP server reads.

Sentiment tracking
How AI describes you, by tone →

Positive and negative, with the exact passages and the sources the AI cited.

All features
See the full platform →

Everything llemmy tracks across the AI answer layer, in one place.

← Back to all features

Talk to your GEO data, free.

Sign up, generate an API key and connect llemmy to Claude or Cursor in minutes. The AI models are included, no extra keys to wrangle.

Start free → Try the free GEO audit