How to integrate Scorecard MCP with Atomic Agent

Atomic Agent is an open-source AI agent that runs on your machine and supports local models through llama.cpp. Connect it to 1,500+ apps through Composio, including Scorecard.

This guide uses Atomic Agent's built-in Composio integration. You need Atomic Agent v0.5.6 or later, your own Composio API key, and a Scorecard account. See the Atomic Agent documentation for installation instructions.

How Atomic Agent connects to Scorecard

Atomic Agent connects to Composio's Tool Router over Streamable HTTP MCP. It discovers the tools needed for your request, and Composio handles account authentication.

Execution and account-connection tools follow Atomic Agent's configured approval policy. Review any approval prompt before allowing an action on your connected account.

Connect Scorecard to Atomic Agent

1. Sign up or sign in to the Composio dashboard. Copy your API key.
2. In Atomic Agent, open the Integrations tab and select Composio. Select API key, press e, paste the key, and press Enter. The tools become available immediately, without a restart.
3. Ask Atomic Agent to do something in Scorecard. It searches Composio for the right tool.
4. On first use, open the sign-in link returned in the chat. Connect your Scorecard account, then return to Atomic Agent to continue.

Headless setup

Add the following line to ~/.atomic-agent/.env, replacing YOUR_COMPOSIO_API_KEY with your key. Start Atomic Agent after saving the file.

The Scorecard MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Scorecard account. It provides structured and secure access to your evaluation projects and documentation, so your agent can manage testsets, organize testcases, configure metrics, track evaluation runs, and search documentation on your behalf.

• Evaluation project management: Have your agent create and maintain evaluation projects for testing your AI systems.
• Testset and testcase organization: Let the agent manage testsets and testcases that cover the scenarios you want to evaluate.
• Systems and metrics setup: Direct your agent to manage evaluated systems and define the metrics used to measure their performance.
• Run and result tracking: Instruct your agent to manage evaluation runs, records, scores, and annotations as results are collected.
• Documentation search: Have your agent search Scorecard SDK documentation for relevant methods, parameters, and usage examples.

Use Scorecard from Atomic Agent

With your account connected, ask Atomic Agent to work with Scorecard in natural language. You can connect more apps through the same Composio integration as you need them.

Visit the Atomic Agent website or inspect the Atomic Agent source code.