The Ragie MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ragie account. It provides structured and secure access to your documents, extracted content, instructions, partitions, and connections, so your agent can ingest, retrieve, update, organize, and delete knowledge on your behalf.
- Document ingestion: Have your agent add documents from files, public web links, text, or JSON content to your Ragie knowledge base.
- Knowledge retrieval: Instruct your agent to find relevant document passages for a question and review document content or individual chunks.
- Document organization: Let the agent list your documents, update their metadata, and create partitions to keep knowledge grouped for specific teams or use cases.
- Entity extraction and ingestion rules: Direct your agent to review entities extracted from documents and create, list, update, or remove instructions that guide document processing.
- Content updates and cleanup: Have your agent refresh documents from public links or new text, inspect available connections, and delete documents you no longer need.