How to connect Tisane 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 Tisane account to Cowork via Composio Connect, enabling it to check this comment for hate speech, summarize topics in this product review, detect sentiment in your latest tweets, and more such actions on your behalf without compromising your account security.

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

The Tisane MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Tisane account. It provides structured and secure access to advanced natural language processing features, so your agent can perform actions like analyzing sentiment, detecting problematic content, extracting topics, and translating or paraphrasing text on your behalf.

• Detailed text analysis: Have your agent analyze any text to detect sentiment, extract entities, identify topics, and uncover other linguistic features in over 27 languages.
• Problematic content detection: Let your agent automatically flag or moderate toxic, abusive, or otherwise problematic content in conversations, comments, or user-generated submissions.
• Topic and entity extraction: Quickly pull out key topics, entities, or subjects from large volumes of text for downstream processing or reporting.
• Semantic similarity scoring: Compare two pieces of text and get a numeric similarity score, helping you find duplicates or measure content overlap.
• Multilingual translation and paraphrasing: Ask your agent to translate text between languages or paraphrase content within the same language to generate fresh variations or adapt for different audiences.