How to integrate Weaviate 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 1,700+ apps through Composio, including Weaviate.

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 Weaviate account. See the Atomic Agent documentation for installation instructions.

How Atomic Agent connects to Weaviate

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 Weaviate 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 Weaviate. It searches Composio for the right tool.
4. On first use, open the sign-in link returned in the chat. Connect your Weaviate 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 Weaviate MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Weaviate account. It provides structured and secure access to your Weaviate Cloud collections, so your agent can answer natural-language questions, run AI-powered searches, apply structured filters, perform aggregations, and return matching data on your behalf.

• Natural-language questions: Have your agent ask questions about your Weaviate collections and turn them into searches or aggregations before providing a final answer.
• Semantic collection search: Let the agent find relevant collection data using AI-powered semantic search rather than relying only on exact keyword matches.
• Structured filtering: Direct your agent to combine semantic search with structured filters to narrow results to the data that matches your criteria.
• Data aggregation: Instruct your agent to generate aggregations from your collection data when answering questions that require grouped or calculated results.
• Matching result retrieval: Have your agent return the Weaviate objects that match a search, so you can work directly with the relevant collection data.

Use Weaviate from Atomic Agent

With your account connected, ask Atomic Agent to work with Weaviate 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.