How to connect Anthropic administrator 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 Anthropic administrator account to Cowork via Composio Connect, enabling it to list all available Anthropic models, get details for a specific Anthropic model, cache a frequently used prompt template, and more such actions on your behalf without compromising your account security.

Connecting Anthropic administrator 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 Anthropic administrator through MCP without you sharing account credentials directly with the agent.

The Anthropic administrator MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Anthropic administrator account. It provides structured and secure access to your Anthropic organization, so your agent can perform actions like generating model completions, managing models, retrieving model details, and optimizing prompt usage on your behalf.

• Seamless message and completion creation: Instruct your agent to generate assistant responses or create message completions within conversation workflows, tailored to your organizational needs.
• Comprehensive model listing and management: Have your agent fetch a full list of available Anthropic models, making it easy to discover and select the right model for any use case.
• Detailed model information retrieval: Let your agent pull specific details about any Anthropic model by its ID, ensuring you always have the latest information on capabilities and configurations.
• Efficient prompt caching and reuse: Enable your agent to store and reuse portions of prompts, reducing both operational costs and latency for high-frequency or repetitive tasks.