The DocuPipe MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your DocuPipe account. It provides structured and secure access to your documents, extraction schemas, processing jobs, and usage data, so your agent can upload and parse documents, extract structured information, track processing, find records, and manage files on your behalf.
- Document upload and parsing: Have your agent submit a local file or remote file for parsing, then retrieve its processed content, page count, metadata, and file details.
- Structured data extraction: Direct your agent to start structured extraction on a processed document and retrieve the completed results with field details.
- Reusable extraction schemas: Let the agent create extraction schemas with custom guidelines, inspect existing schemas, and list the schemas available in your workspace.
- Document and job tracking: Instruct your agent to find documents by dataset, creation time, filename, or search terms, and check the progress of processing jobs.
- Workspace management and usage: Have your agent review plan and credit usage, inspect job activity, and permanently delete one or several documents when they are no longer needed.