You can access real-time pricing, speed metrics, and benchmark scores for 300+ LLMs through an MCP server created by Artificial Analysis. Install and connect to this server from your MCP client, then list models, compare metrics, and retrieve detailed model information to inform your choices and benchmarking efforts.

How to use

Use your MCP client to interact with the Artificial Analysis MCP Server. You can list available models with optional filters, sort by any metric, and drill down into a specific model to view pricing, speed, and benchmark scores. Typical tasks include finding the fastest models, identifying the best price-per-token options, and comparing intelligence and coding benchmarks across providers.

How to install

# Option 1: Claude CLI command to add the MCP server
claude mcp add artificial-analysis -e AA_API_KEY=your-key -- npx -y artificial-analysis-mcp

# Option 2: Add directly from GitHub (MCP setup via Claude)
claude /mcp add https://github.com/davidhariri/artificial-analysis-mcp

If you prefer manual configuration, add the MCP server configuration to your Claude settings file so it connects automatically. Create or edit your file at ~/.claude/settings.json and include the MCP server entry shown in the snippet below.

Additional content

{
  "mcpServers": {
    "artificial_analysis": {
      "command": "npx",
      "args": ["-y", "artificial-analysis-mcp"],
      "env": {
        "AA_API_KEY": "your-api-key"
      }
    }
  }
}

{
  "AA_API_KEY": "your-api-key"
}

Get your API key by signing up with Artificial Analysis and locating it in your account settings.

## Configuration and security

Environment variable you need to run the MCP server: `AA_API_KEY`. This key authorizes calls to the Artificial Analysis API. Treat it as a secret and do not expose it in logs or public repositories.

## Development

Install dependencies

npm install

Build the server

npm run build

Run locally (provide your API key)

AA_API_KEY=your-key node dist/index.js

## Available tools

### list\_models

List all available LLM models with optional filtering and sorting. You can filter by creator, sort by a field, and limit the number of results.

### get\_model

Get detailed information about a specific model, including pricing, speed metrics, and all benchmark scores.