AT

Atla

Created 5 months ago

An MCP server implementation providing a standardized interface for LLMs to interact with the Atla API.

development documentation public

What is Atla?

Enable AI agents to interact with the [Atla API](https://docs.atla-ai.com/) for state-of-the-art LLMJ evaluation.

Documentation

Available Tools

  • evaluate_llm_response: Evaluate an LLM's response to a prompt using a given evaluation criteria.
  • evaluate_llm_response_on_multiple_criteria: Evaluate an LLM's response to a prompt across multiple evaluation 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:

ATLA_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.

Claude Desktop

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

Cursor

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

Server Config

{
  "mcpServers": {
    "atla-server": {
      "command": "npx",
      "args": [
        "atla"
      ]
    }
  }
}

Links & Status

Repository: github.com
Hosted: No
Global: No
Official: No

Project Info

Hosted Featured
Created At: Jul 02, 2025
Updated At: Aug 07, 2025
Author: Atla AI
Category: official
License: MIT License
Tags:
development documentation public