Atla

What is Atla MCP Server?

The Atla MCP Server provides a standardized interface for Large Language Models (LLMs) to interact with the Atla API, which is designed for state-of-the-art LLM-as-a-judge (LLMJ) evaluation. It allows AI agents to evaluate the quality of LLM responses based on specified criteria.

How to use the project?

To use the Atla MCP Server, you need an Atla API key. The server can be run manually using uvx after setting the ATLA_API_KEY environment variable. It can then be connected to various MCP clients like the OpenAI Agents SDK.

Key Features

• LLM Response Evaluation: Evaluate an LLM's response to a prompt against single or multiple criteria.
• Scoring and Feedback: Provides a numerical score and a textual critique for each evaluation.
• Easy Integration: Designed for straightforward integration with MCP clients.

Use Cases

• Model Performance Monitoring: Continuously evaluate and monitor the performance of your LLMs in production.
• A/B Testing: Compare the responses of different models or prompts to identify the best-performing ones.
• Improving AI Agent Quality: Use the feedback from evaluations to fine-tune and improve the quality of your AI agents' responses.

FAQ

Q: What is Atla? A: Atla is a platform that provides state-of-the-art tools for evaluating and improving Large Language Models.

Q: Do I need an API key to use the server? A: Yes, an Atla API key is required to use the MCP server. You can sign up on the Atla website to get one.

Q: What are the main evaluation tools available? A: The server provides two main tools: evaluate_llm_response for single-criterion evaluation and evaluate_llm_response_on_multiple_criteria for multi-criteria evaluation.

Atla MCP Server

An MCP server implementation providing a standardized interface for LLMs to interact with the Atla API for state-of-the-art LLMJ evaluation.

Learn more about Atla here. Learn more about the Model Context Protocol here.

Available Tools

• evaluate_llm_response: Evaluate an LLM's response to a prompt using a given evaluation criteria. This function uses an Atla evaluation model under the hood to return a dictionary containing a score for the model's response and a textual critique containing feedback on the model's response.
• evaluate_llm_response_on_multiple_criteria: Evaluate an LLM's response to a prompt across multiple evaluation criteria. This function uses an Atla evaluation model under the hood to return a list of dictionaries, each containing an evaluation score and critique for a given criteria.

Usage

To use the MCP server, you will need an Atla API key. You can find your existing API key here or create a new one here.

Installation

We recommend using uv to manage the Python environment. See here for installation instructions.

Manually running the server

Once you have uv installed and have your Atla API key, you can manually run the MCP server using uvx (which is provided by uv):

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

Connecting to the server

Having issues or need help connecting to another client? Feel free to open an issue or contact us!

OpenAI Agents SDK

For more details on using the OpenAI Agents SDK with MCP servers, refer to the official documentation.

1. Install the OpenAI Agents SDK:

pip install openai-agents

2. Use the OpenAI Agents SDK to connect to the server:

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:
    ...

Claude Desktop

For more details on configuring MCP servers in Claude Desktop, refer to the official MCP quickstart guide.

1. Add the following 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.

You should now see options from atla-mcp-server in the list of available MCP tools.

Cursor

For more details on configuring MCP servers in Cursor, refer to the official documentation.

1. Add the following 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 now see atla-mcp-server in the list of available MCP servers.

Contributing

Contributions are welcome! Please see the CONTRIBUTING.md file for details.

License

This project is licensed under the MIT License. See the LICENSE file for details.