Atla
Created 5 months ago
An MCP server implementation providing a standardized interface for LLMs to interact with the Atla API.
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"
]
}
}
}