PDF Reader MCP

Example Use Cases

• 1

  Extract and ingest text from local PDF documents mounted into a container for indexing, search, or summarization workflows.

• 2

  Fetch PDFs over HTTP(S) and convert them to plaintext for downstream analysis, extraction, or QA tasks.

• 3

  Reliable, standardized JSON output and clear error messages when automating bulk PDF processing in pipelines.

Description

This MCP server reads and extracts text from PDF files provided either as local files (via a mounted volume) or as URLs. It uses PyPDF2 for parsing and requests for fetching remote PDFs, and it returns consistent JSON responses including error details for common failure cases. The server is distributed as a Docker image for simple deployment and supports auto-detection of PDF encoding and robust error handling.