PDF

Provides metadata, text extraction, search, and smart chunking for large PDFs via an MCP client.

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "volume19-pdf-mcp-server": {
      "command": "python",
      "args": [
        "c:\\Users\\Will\\pdf-mcp-server\\server.py"
      ]
    }
  }
}

You run a PDF MCP Server to process large PDF files by extracting text, searching content, and computing optimal processing chunks. It handles metadata, supports contextual search, and processes PDFs in manageable chunks so you can analyze big documents efficiently.

How to use

You connect an MCP client to the PDF MCP Server to perform common tasks like inspecting metadata, extracting text from specific page ranges, searching within the document, and planning chunked processing. Use the client to request these actions, then receive structured results with page references, contexts, and chunk ranges. This server runs locally on your machine and uses your compute resources, so you can process large PDFs without relying on external services.

Typical workflows you can perform include: getting file metadata to learn page count and author details, extracting text from defined page ranges with optional character limits, searching for terms across the document with contextual snippets, and calculating optimal page chunks for large files to balance performance with completeness.

How to install

Prerequisites: Python is installed on your system and available in your command line.

Install Python dependencies used by the server.

Install required Python packages listed by the project.

Configuration and startup

{
  "mcpServers": {
    "pdf-processor": {
      "command": "python",
      "args": ["c:\\Users\\Will\\pdf-mcp-server\\server.py"]
    }
  }
}

Notes and examples

This server uses pdfplumber for high-quality text extraction and pypdf for metadata and PDF structure. It runs locally and processes PDFs in chunks to avoid file size limitations. It can handle PDFs that are encrypted unless a password is required.

Troubleshooting

If the server doesn’t appear in the client interface, ensure the path to the startup command is correct and restart the client after configuration changes. Confirm Python is accessible from the command line.

Security notes

Operate the server on trusted PDFs and control access to local resources to prevent unauthorized access to sensitive documents.

Notes on capabilities

The server provides a structured API for common PDF tasks: metadata retrieval, text extraction with per-range control, search with context, and chunking strategy for large PDFs.

Available tools

pdf_get_metadata

Get metadata about a PDF file, including file size, page count, title, author, and other metadata.

pdf_extract_text

Extract text from a range of pages with optional start_page, end_page, and max_chars to control size and content.

pdf_search

Search for text within a PDF with optional context around matches and a limit on results.

pdf_get_chunks

Calculate an optimal chunking strategy for large PDFs by specifying max characters per chunk and overlap between chunks.