MCP Enabled PDF Reader

Name: MCP Enabled PDF Reader
Author: karateboss

@karateboss

代码仓库

关于 MCP Enabled PDF Reader

Model Context Protocol (MCP) server to read a single pdf document

基本信息

分类

文件与存储

许可证

Apache-2.0

运行时

python

传输方式

stdio

发布者

karateboss

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "mcp-pdf-reader": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/karateboss/mcp_pdf_reader@main",
        "mcp_pdf_reader"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is MCP Enabled PDF Reader?

MCP Enabled PDF Reader is a Model Context Protocol (MCP) server that exposes a single tool called read_pdf to read a single PDF document. It is designed for use with MCP‑enabled AI tools such as Claude Desktop and LibreChat with Ollama.

How to use MCP Enabled PDF Reader?

Install Python 3.10 or higher and the uv package manager. Then add the provided JSON configuration to your claude_desktop_config.json to register the server. The tool is invoked by the MCP client when the AI agent calls read_pdf.

Key features of MCP Enabled PDF Reader

Exposes one tool: read_pdf
Reads a single PDF document per invocation
No maximum PDF file size (token limit is the limiting factor)
Tested with Claude Desktop and LibreChat with Ollama
Configured via claude_desktop_config.json using uvx
Developed and maintained by Safe Swiss Cloud

Use cases of MCP Enabled PDF Reader

Reading PDF documents directly through a Claude Desktop conversation
Extracting text from PDFs using LibreChat with an Ollama backend
Integrating PDF content into any MCP‑compatible AI workflow

FAQ from MCP Enabled PDF Reader

What does MCP Enabled PDF Reader do?

It provides a Model Context Protocol server that exposes the read_pdf tool, allowing MCP‑enabled AI assistants to read and process the content of a single PDF file.