OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
MCP & Tooling

Pdf MCP

Pdf MCP is an open-source MCP server that gives compatible AI agents tools to search and read one PDF or a folder of PDFs. Its tools support hybrid keyword and semantic search, selected-page retrieval, document overviews, and extraction of tables, images and scanned text.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Pdf MCP — OpenViST project profile in MCP & Tooling.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Pdf MCP when an MCP-compatible agent needs targeted access to a PDF or collection, especially when searching many documents or working with scanned or complex page layouts.

Who it is for

  • People using MCP-compatible AI agents to find information in PDFs.
  • Developers building PDF question-answering or document retrieval workflows.
  • Teams working with scanned, multi-column, or CJK-layout PDF documents.

Documented uses

  • Search a PDF or folder by keyword and meaning.
  • Locate relevant passages and read selected pages rather than whole large documents.
  • Extract tables, images or OCR text for an agent workflow.
  • Triage a folder of PDFs before searching across the collection.
Before you choose

Requirements & limits

The repository documents a Claude Desktop extension and Python command-line installation for MCP clients. The server requires Python 3.10 or later; scanned-page OCR requires Tesseract. The project is licensed under MIT.

  • Choose the connection route that matches the agent environment: Claude Desktop extension, Python command-line server, or imported Python functions.
  • Tesseract is an additional prerequisite for OCR of scanned pages in the command-line setup.
  • CUDA is optional and described as an acceleration for warming large folders on an NVIDIA card.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Connect Pdf MCP to Claude Code

Install the Pdf MCP command and add it as a Claude Code MCP server.

Before you start

  • Python 3.10 or later
  • Claude Code
  • uv or pipx

Steps

  1. Install the pdf-mcp command with the command below or pipx install pdf-mcp.

    Documented command
    uv tool install pdf-mcp

  2. Register it with Claude Code using claude mcp add pdf-mcp -- pdf-mcp.

  3. Ask the agent to read a PDF.

Expected outcome

Claude Code can use Pdf MCP tools to search and read PDF material.

Guide limitations

  • OCR for scanned pages also requires Tesseract.
  • The README directs users of other MCP clients to separate client instructions.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
jztan/pdf-mcp · Official homepage title · retained in its source language
How we review sourcesSuggest a correction