---
title: Overview
description: Connect SeeLLM to your AI assistant via the Model Context Protocol (MCP).
audience: [human, agent]
type: reference
version: v1
stability: stable
lastVerified: "2026-08-01"
prerequisites: []
related: [/docs/mcp/setup/, /docs/mcp/tools/, /docs/api/authentication/]
artifacts: []
---

## What is MCP?

The [Model Context Protocol](https://modelcontextprotocol.io) (MCP) is an open standard that lets AI assistants connect to external data sources. SeeLLM's MCP server gives your AI assistant direct access to your traffic intelligence data.

Instead of switching to a dashboard, you can ask your AI assistant questions like:

- "What's my AI traffic trend this month?"
- "Which AI platforms are visiting my site most?"
- "What would happen if I blocked GPTBot?"

## Setup

### Prerequisites

You need a SeeLLM API key. Generate one in your [dashboard](https://app.seellm.com) under Settings > API Keys.

### Claude Desktop

Add this to your Claude Desktop config (`~/Library/Application Support/Claude/claude_desktop_config.json`):

```json
{
  "mcpServers": {
    "seellm": {
      "url": "https://api.seellm.link/mcp",
      "headers": {
        "Authorization": "Bearer sk_live_your_api_key_here"
      }
    }
  }
}
```

### Cursor

Add this to your project's `.cursor/mcp.json`:

```json
{
  "mcpServers": {
    "seellm": {
      "url": "https://api.seellm.link/mcp",
      "headers": {
        "Authorization": "Bearer sk_live_your_api_key_here"
      }
    }
  }
}
```

### Claude Code

Add to your project's `.mcp.json`:

```json
{
  "mcpServers": {
    "seellm": {
      "type": "url",
      "url": "https://api.seellm.link/mcp",
      "headers": {
        "Authorization": "Bearer sk_live_your_api_key_here"
      }
    }
  }
}
```

## Next Steps

- See the full [MCP Tools Reference](/docs/mcp/tools/) for all available tools
- Check [Setup Guide](/docs/mcp/setup/) for detailed configuration per platform