How to connect Moderation API 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 Moderation API account to Cowork via Composio Connect, enabling it to review flagged comments from today, block authors with repeated policy violations, approve safe posts in review queue, and more such actions on your behalf without compromising your account security.

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

The Moderation API MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Moderation API account. It provides structured and secure access to your moderation workflows, review queues, actions, and wordlists, so your agent can evaluate content, submit items for review, inspect queues, resolve reviewed items, and apply moderation actions on your behalf.

• Content policy evaluation: Have your agent evaluate content without storing it, then report policy findings and the recommended moderation action.
• Content submission and review: Let the agent submit content for moderation so it can be retained and added to a review queue based on your project settings.
• Review queue management: Direct your agent to check queue totals, list and filter moderation items, and mark reviewed items as resolved or pending.
• Moderation action execution: Instruct your agent to view available moderation actions and apply the appropriate action to content or authors.
• Wordlist management: Have your agent list wordlists, inspect their current words, and add or remove terms from an existing wordlist.