Ragie Model Context Protocol Server

What is Ragie Model Context Protocol Server?

A Model Context Protocol (MCP) server that provides access to Ragie's knowledge base retrieval capabilities. It implements the Model Context Protocol to enable AI models to retrieve information from a Ragie knowledge base.

How to use Ragie Model Context Protocol Server?

Install and run with npx: set the RAGIE_API_KEY environment variable and optionally use --description and --partition flags. Configure the server for use with Cursor or Claude Desktop by adding a mcp.json or claude_desktop_config.json file.

Key features of Ragie Model Context Protocol Server

• Provides a retrieve tool for searching the knowledge base
• Accepts optional parameters: topK, rerank, and recencyBias
• Customizable tool description via --description flag
• Partition filtering via --partition flag
• Easy integration with Cursor and Claude Desktop

Use cases of Ragie Model Context Protocol Server

• Query a company knowledge base for relevant information
• Retrieve the most relevant text chunks from a set of documents
• Bias search results towards recent or high-relevance content
• Integrate knowledge base search into AI-assisted coding workflows

FAQ from Ragie Model Context Protocol Server

What does the retrieve tool do?

Searches the Ragie knowledge base for chunks matching a query and returns an array of content with matching text.

What prerequisites are required?

Node.js >= 18 and a valid Ragie API key set as the RAGIE_API_KEY environment variable.

How can I customize the tool's description?

Use the --description (or -d) flag when starting the server, e.g., --description "Search the company knowledge base".

How do I filter retrieval to a specific partition?

Use the --partition (or -p) flag with the partition ID, e.g., --partition your_partition_id.

How do I configure the server with Claude Desktop?

Add a claude_desktop_config.json file with the server command and environment variables, then restart Claude Desktop.