Atla MCP server

Atla MCP Server provides a standardized interface for LLMs to interact with the Atla API for state-of-the-art LLMJ evaluation. It enables you to evaluate LLM responses against specific criteria using Atla's evaluation models, returning detailed scores and critiques.

Installation

To use the Atla MCP server, you'll need an Atla API key, which you can find or create at Atla sign-in or Atla sign-up.

The recommended installation method uses uv to manage the Python environment. First, install uv by following the uv installation instructions.

Once you have uv installed, you can run the MCP server using uvx:

ATLA_API_KEY=<your-api-key> uvx atla-mcp-server

Available Tools

The server provides two main evaluation tools:

• evaluate_llm_response: Evaluates an LLM's response to a prompt using a given evaluation criteria, returning a score and textual critique.
• evaluate_llm_response_on_multiple_criteria: Evaluates an LLM's response across multiple evaluation criteria, returning a list of dictionaries containing scores and critiques for each criterion.

Connecting to the Server

OpenAI Agents SDK

To connect using the OpenAI Agents SDK:

1. Install the SDK:

pip install openai-agents

2. Connect to the server in your Python code:

import os

from agents import Agent
from agents.mcp import MCPServerStdio

async with MCPServerStdio(
        params={
            "command": "uvx",
            "args": ["atla-mcp-server"],
            "env": {"ATLA_API_KEY": os.environ.get("ATLA_API_KEY")}
        }
    ) as atla_mcp_server:
    # Your code using the server
    pass

Claude Desktop

To configure the server in Claude Desktop:

1. Add this configuration to your claude_desktop_config.json file:

{
  "mcpServers": {
    "atla-mcp-server": {
      "command": "uvx",
      "args": ["atla-mcp-server"],
      "env": {
        "ATLA_API_KEY": "<your-atla-api-key>"
      }
    }
  }
}

2. Restart Claude Desktop to apply the changes.

After restarting, you should see options from atla-mcp-server in the list of available MCP tools.

Cursor

To configure the server in Cursor:

1. Add this configuration to your .cursor/mcp.json file:

{
  "mcpServers": {
    "atla-mcp-server": {
      "command": "uvx",
      "args": ["atla-mcp-server"],
      "env": {
        "ATLA_API_KEY": "<your-atla-api-key>"
      }
    }
  }
}

You should then see atla-mcp-server in the list of available MCP servers in Cursor.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.