Pdf(paper) Figures Extraction Mcp Serever

Name: Pdf(paper) Figures Extraction Mcp Serever
Author: vlln

@vlln

代码仓库

关于 Pdf(paper) Figures Extraction Mcp Serever

暂无概览

#pdf #figure-extraction #mcp-server

基本信息

分类

数据与分析

传输方式

stdio

发布者

vlln

提交者

赵刚

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "pdffigures-mcp-server": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "pdf-extraction",
        "."
      ]
    }
  }
}

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 Pdf(paper) Figures Extraction Mcp Serever?

Pdf(paper) Figures Extraction Mcp Serever is a FastAPI-based service that extracts figures, tables, captions, and section titles from PDF documents. It wraps PDFFigures 2.0, a figure extraction system by the Allen Institute for AI designed for scholarly computer science papers, and exposes the functionality as both an HTTP API and an MCP tool for integration with AI agents and workflows.

How to use Pdf(paper) Figures Extraction Mcp Serever?

Deploy using Docker: clone the repository, build the image, and run the container. After deployment, send a POST request to /api/extract with a PDF file or a PDF URL. The MCP tool (extract_figures_from_pdf) can be invoked via an HTTP request to the /mcp endpoint. The CLI can also be used directly via python figure_extractor.py <path_to_pdf>.

Key features of Pdf(paper) Figures Extraction Mcp Serever

Extracts figures, tables, captions, and section titles from PDFs
Supports both local and remote PDF files
Provides statistics of extracted tables and figures
Docker support for easy deployment and scalability
Offers visualization options for PDF parsing
MCP server exposes extraction as a tool for AI agents

Use cases of Pdf(paper) Figures Extraction Mcp Serever

Machine learning dataset creation from clinical trial reports and research papers
Clinical research data mining for automated figure and table cataloging
Academic literature review and education for compiling visual libraries

FAQ from Pdf(paper) Figures Extraction Mcp Serever

What types of content does Pdf(paper) Figures Extraction Mcp Serever extract?

It extracts figures, tables, captions, and section titles from PDF documents, particularly from scholarly computer science papers.

Can I use Pdf(paper) Figures Extraction Mcp Serever without Docker?

Yes, the service can also be run directly using the CLI tool figure_extractor.py after setting up the required dependencies.

What is the default MCP server URL?

The default MCP server URL is http://localhost:5001/mcp.

What is PDFFigures 2.0 and how does this server relate?

PDFFigures 2.0 is a Scala-based project by the Allen Institute for AI that extracts figures from scholarly documents. This server serves as a Python-FastAPI wrapper around that system, providing an HTTP interface and an MCP tool.

Is there a way to test the API after deployment?

Yes, after running the server, navigate to http://localhost:5001/docs in a web browser to view the API documentation and test endpoints interactively.