Custom PDF

Provides a custom PDF processing MCP server for reading text, extracting tables, gathering metadata, and listing PDFs with directory scoping.

python

0

GitHub Stars

python

Language

5 months ago

First Indexed

2 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": {
    "waicy--pdf-mcp-": {
      "command": "uv",
      "args": [
        "run",
        "pdf-mcp"
      ]
    }
  }
}

You run a specialized MCP server that processes PDFs, enabling text extraction, table data capture, metadata retrieval, and directory scanning—all while restricting access to your current working directory. This server is designed to fit into your MCP workflow so you can automate PDF handling from your preferred client.

How to use

Connect to the Custom PDF MCP Server from your MCP client. You can choose either the local stdio workflow or run the server via the recommended UV-based command, then invoke the provided functions to read text, extract tables, fetch info, or list PDFs.

How to install

Prerequisites you need before starting:

Python (for the script option)
UV (for the fast local runtime)
Git (to clone the project repository)

# Prerequisites check (example on Unix-like systems)
python --version
uv --version
git --version

# Method 1: Using uv (recommended)
# Clone the project
git clone https://github.com/Waicy/-pdf-mcp-.git
cd pdf-mcp

# Create a virtual environment and install dependencies
uv sync

# Method 2: Using pip
# Clone the project
git clone https://github.com/yourusername/pdf-mcp.git
cd pdf-mcp

# Install dependencies
pip install . --index-url https://pypi.tuna.tsinghua.edu.cn/simple

Starting the server and basic usage

You can start the server using either the UV-based command or the traditional Python script. Choose the method you installed during setup.

# If using UV (recommended)
uv run pdf-mcp

# If using the traditional Python script
python src/pdf_mcp_server.py

Available tools

read_pdf_text

Reads a PDF file and extracts text content with optional page range and table extraction.

get_pdf_info

Retrieves basic information and metadata for a PDF file.

list_pdfs_in_directory

Lists all PDF files within a specified directory.