Keywords AI MCP Server

Redirecting to documentation...

If you are not redirected automatically, click here.

Model Context Protocol server for accessing Keywords AI data from your AI assistantFeatures

Logs - Query and filter LLM request logs with powerful filtering

Traces - View complete execution traces with span trees

Customers - Access customer data and budget information

Prompts - Manage prompt templates and versions

Quick Start

Mode 1: HTTP Streaming - Public Service

Use the hosted endpoint where each user provides their own API key:

{
  "mcpServers": {
    "keywords-ai": {
      "url": "https://mcp.keywordsai.co/api/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_KEYWORDS_AI_API_KEY"
      }
    }
  }
}

Mode 2: Local Stdio (Personal Use)

Run locally for development - simplest setup:

git clone https://github.com/Keywords-AI/keywordsai-mcp.git
cd keywordsai-mcp
npm install && npm run build

Configure your MCP client (~/.cursor/mcp.json):

{
  "mcpServers": {
    "keywords-ai": {
      "command": "node",
      "args": ["/path/to/keywordsai-mcp/dist/lib/index.js"],
      "env": {
        "KEYWORDS_API_KEY": "your_api_key"
      }
    }
  }
}

Mode 3: HTTP Streaming - Private Deployment

Deploy to Vercel with API key stored as environment variable. No client-side key needed:

Clone: git clone https://github.com/Keywords-AI/keywordsai-mcp
Deploy: vercel deploy --prod
Set KEYWORDS_API_KEY in Vercel Dashboard → Environment Variables

Configure your MCP client:

{
  "mcpServers": {
    "keywords-ai": {
      "url": "https://your-project.vercel.app/mcp"
    }
  }
}

Available Tools