How to connect PromptHub 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 PromptHub account to Cowork via Composio Connect, enabling it to retrieve latest PromptHub production prompt, run PromptHub support prompt with variables, compare PromptHub revisions before deployment, and more such actions on your behalf without compromising your account security.

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

The PromptHub MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your PromptHub account. It provides structured and secure access to your teams, projects, versioned prompts, and model configurations, so your agent can identify your current team, list projects, retrieve the latest committed prompts, and run projects on your behalf.

• Team identification: Have your agent find the current PromptHub team associated with your connected account.
• Project discovery: Let the agent list your team's projects and narrow them by group, model, or provider.
• Latest prompt retrieval: Direct your agent to fetch a project's latest committed prompt and model configuration, including content from a selected branch.
• Variable resolution: Instruct your agent to retrieve committed prompts with their variables resolved for immediate use.
• Project execution: Have your agent run a committed project with optional variables and return the generated text along with usage, cost, and timing details.