How to connect Metaphor to Claude Cowork

Cowork is Anthropic's AI agent for knowledge work. Think of it as Claude Code for everything else. It works autonomously with your computer, local files, and applications to accomplish complex tasks.

This guide walks you through the easiest and most secure way to connect your Metaphor account to Cowork via Composio Connect, enabling it to fetch content of recent AI research links, get metadata for top-shared tech articles, retrieve full text from specific document IDs, and more such actions on your behalf without compromising your account security.

Connecting Metaphor to Claude Cowork

1. Open Customize

In Claude Desktop, click Customize in the left sidebar, then select Connectors and click the + icon at the top.

2. Add the Composio MCP server

Click Add custom connector and paste in the Composio MCP server URL:

Claude Cowork is Anthropic's agent for general knowledge work. It can use your computer, files, and connected applications to complete longer-running tasks across your work tools.

With Composio Connect, Cowork can securely access apps like Metaphor through MCP without you sharing account credentials directly with the agent.

The Metaphor MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Metaphor account. It provides structured and secure access to your neural search data, so your agent can perform actions like retrieving document contents, extracting metadata, and surfacing relevant knowledge from indexed documents on your behalf.

• Bulk document content retrieval: Fetch the full parsed HTML or text of multiple documents at once using their IDs, making research and data extraction effortless.
• Metadata extraction and analysis: Have your agent pull structured metadata (like title, source, or date) for any set of indexed documents to power downstream tasks or summaries.
• Context-aware content delivery: Provide your agent with in-depth context from relevant documents to inform generation, summarization, or Q&A workflows.
• Automated research pipelines: Let the agent orchestrate the retrieval of primary sources and their contents, enabling advanced aggregation or cross-document insights.