How to connect VLM Run 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 VLM Run account to Cowork via Composio Connect, enabling it to extract invoice fields from uploaded PDFs, classify product images by defect type, evaluate extraction quality against gold labels, and more such actions on your behalf without compromising your account security.

Connecting VLM Run 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 VLM Run through MCP without you sharing account credentials directly with the agent.

The VLM Run MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your VLM Run account. It provides structured and secure access to your multimodal agents, files, skills, extraction workflows, and runs, so your agent can upload files, extract structured data, execute agents, create reusable skills, and track results on your behalf.

• Structured data extraction: Have your agent extract structured JSON from documents, images, videos, or audio using a supported domain, custom schema, or existing skill.
• Multimodal agent execution: Direct your agent to choose an available VLM Run agent or provide an inline configuration, then run it against multimodal inputs.
• File and skill management: Let the agent upload local files, find previously uploaded files, browse existing skills, or create a reusable skill from an uploaded zip, prompt, or chat session.
• Run tracking and result retrieval: Instruct your agent to list extraction and agent runs, check work in progress, and retrieve completed results.
• Schema and artifact discovery: Have your agent explore supported extraction domains and schemas, then list artifacts created during a chat session or agent execution.