Cherry FAQs

Question 1

Which AI IDEs and clients are compatible with Cherry?

Accepted Answer

Cherry is designed to integrate seamlessly with AI IDEs and clients that support the Model Context Protocol (MCP). Confirmed integrations include opencode, Cursor, and Claude Desktop.

Question 2

What tools does Cherry provide for managing knowledge bases?

Accepted Answer

Cherry includes powerful MCP tools: `list_knowledge_bases` to display details of all available KBs (name, path, vector count), and `search_knowledge` to execute vector similarity searches and retrieve relevant document fragments from your Cherry Studio data.

Question 3

What is Cherry and its main purpose?

Accepted Answer

Cherry (cherry-mcp) acts as an MCP server, exposing your local Cherry Studio knowledge bases directly to AI clients and integrated development environments (IDEs) like opencode, Cursor, and Claude Desktop, enabling direct search and contextual understanding.

Question 4

How does Cherry improve AI client interactions?

Accepted Answer

By leveraging the Model Context Protocol (MCP), Cherry allows AI clients to perform vector similarity searches on your private knowledge bases. This retrieves highly relevant context, significantly enhancing the accuracy and performance of Retrieval Augmented Generation (RAG) systems.

Question 5

Can I customize the embedding models used by Cherry?

Accepted Answer

Yes, Cherry offers extensive customization for embedding models. You can configure the embedding API URL, model ID, and vector dimension using CLI arguments or environment variables, accommodating various local or remote embedding services.

Cherry

Cherry

Key Features

Use Cases

Key Features

Use Cases