广告合作
MCP.so
登录
P

Pdf(paper) Figures Extraction MCP Serever

@vlln

代码仓库

基本信息

分类

数据与分析

传输方式

stdio

作者

vlln

提交者

赵刚

关于 Pdf(paper) Figures Extraction MCP Serever

暂无概览

#pdf#figure-extraction#mcp-server

Pdf(paper) Figures Extraction MCP Serever 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",
        "."
      ]
    }
  }
}

Pdf(paper) Figures Extraction MCP Serever 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

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

常见问题

1

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.

2

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.

3

What is the default MCP server URL?

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

4

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.

5

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.

评论

数据与分析 分类下的更多 MCP 服务器

Octolens

Octolens

Give your AI agents every brand mention across the internet — 15+ platforms, AI-filtered, one structured feed.

Lawstronaut Legal Research

Lawstronaut-FZCO

Connect your AI to millions of laws and court cases! Lawstronaut is the infrastructure layer that connects AI agents and software to millions of legal documents across 150+ jurisdictions, structured legal data, continuou

1

Bounce Watch - Company Signal Intelligence

bouncewatch

Bounce Watch tells you what just changed at a company, and when. Who raised money. Who hired a senior person. Who opened an office, won a customer, or announced a partnership. Every event carries its own date, so you ca

NeuralVerge

NeuralVerge is the data layer for agentic AI. Ask a question in plain language and get a structured, cited answer drawn from 300+ sources — e-commerce marketplaces, corporate registries, company intelligence, enrichme

Subtext

Subtext by Fullstory

Session replay, built for agents. Subtext is agentic session review: it captures production sessions of your app and connects them to your coding agent — Claude Code, Cursor, Codex, Devin, your own harness — so it can

9
广告合作