Enable AI agents to interact with the Atla API for state-of-the-art LLMJ evaluation.
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.
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.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.
We recommend using
uv
to manage the Python environment. See here for installation instructions.
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
Having issues or need help connecting to another client? Feel free to open an issue or contact us!
For more details on using the OpenAI Agents SDK with MCP servers, refer to the official documentation.
pip install openai-agents
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:
...
For more details on configuring MCP servers in Claude Desktop, refer to the official MCP quickstart guide.
claude_desktop_config.json
file:{
"mcpServers": {
"atla-mcp-server": {
"command": "uvx",
"args": ["atla-mcp-server"],
"env": {
"ATLA_API_KEY": "<your-atla-api-key>"
}
}
}
}
You should now see options from atla-mcp-server
in the list of available MCP tools.
For more details on configuring MCP servers in Cursor, refer to the official documentation.
.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.
Contributions are welcome! Please see the CONTRIBUTING.md file for details.
This project is licensed under the MIT License. See the LICENSE file for details.
Interact with your crash reporting and real using monitoring data on your Raygun account
A secure MCP server for executing terminal commands with controlled directory access and command permissions.
MCP server to provide Jira Tickets information to AI coding agents like Cursor.
Provides tools for geospatial analysis within Jupyter notebooks.
Interacting with Phabricator API
Navigate your OpenTelemetry resources, investigate incidents and query metrics, logs and traces on Dash0.
Integrates with Language Server Protocol (LSP) to provide features like code completion, diagnostics, and hover information.
Bootstrap Model Context Protocol (MCP) servers and clients in TypeScript with best practices, examples, and proper tooling setup.
A service framework supporting the Model Context Protocol (MCP) to integrate enterprise systems and AI platforms via RESTful, gRPC, and Dubbo protocols.
Interact with Homebrew (the package manager for macOS and Linux) using natural language commands.