PDF Processor MCP Server
PDF处理器MCP服务器
一个模型上下文协议 (MCP) 服务器,用于处理 PDF 文档,并具备 LaTeX 公式提取等高级功能。该服务器使 Claude 能够从 PDF 文档中获取、处理和提取信息,包括 LaTeX 数学公式。
特征
从 URL 获取 PDF
从 PDF 中提取文本
LaTeX 公式识别和提取
通过 MCP 与 Claude 集成
Related MCP server: MCP PDF Reader
安装
标准安装
pip install -e .安装 Claude Desktop/Claude Code
要将此 MCP 服务器与 Claude Desktop 或 Claude Code 一起使用:
如果尚未安装,请安装 MCP CLI 工具:
pip install "mcp[cli]"使用 MCP CLI 工具安装服务器:
mcp install /path/to/pdf_tool_server.py --with-editable /path/to/mcp_pdf_processor例如,如果您已将此存储库克隆到
~/mcp_pdf_processor:mcp install ~/mcp_pdf_processor/pdf_tool_server.py --with-editable ~/mcp_pdf_processor使用 MCP Inspector 进行开发:
mcp dev /path/to/pdf_tool_server.py --with-editable /path/to/mcp_pdf_processor在 Claude Desktop 中,您现在可以通过以下命令在对话中使用 PDF_TOOLS 服务器:
/mcp PDF_TOOLS fetch_pdf url=https://example.com/document.pdf /mcp PDF_TOOLS process_pdf hash_id=<HASH_ID> extract_latex=true /mcp PDF_TOOLS read_processed_pdf filename=<FILENAME>
用法
独立运行
python pdf_tool_server.py环境变量
OUTPUT_DIR:存储已处理 PDF 的目录(默认值:llm_output)PYTHONPATH:设置为包含 mcp_pdf_processor 包的目录
与 Claude 一起使用
当服务器注册完成后,你可以要求 Claude 执行以下操作:
“获取并分析 [URL] 处的 PDF”
“从 [URL] 处的 PDF 中提取 LaTeX 方程式”
“总结 [URL] 处的 PDF 内容”
要求
该服务器需要以下主要依赖项:
Python 3.9 或更高版本
pymupdf:PDF处理和文本提取mcp:模型上下文协议支持pydantic:数据验证和序列化aiohttp:异步 HTTP 客户端/服务器torch:用于 LaTeX 方程提取(可选)pix2tex:用于 LaTeX 方程式识别(可选)
请参阅pyproject.toml以获取依赖项和版本要求的完整列表。
使用示例
以下是使用 Claude Desktop 的 PDF 处理器的完整示例工作流程:
# 1. Fetch a PDF without reading it
/mcp PDF_TOOLS fetch_pdf url=https://arxiv.org/pdf/2505.05522
# This returns a hash_id, which you'll use in the next step
# 2. Process the PDF with LaTeX extraction
/mcp PDF_TOOLS process_pdf hash_id=<HASH_ID> extract_latex=true
# This returns a filename for the processed output
# 3. Read the processed content
/mcp PDF_TOOLS read_processed_pdf filename=<FILENAME>
# Now Claude can analyze the PDF content, including any LaTeX equations执照
麻省理工学院
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseAquality-maintenanceA Model Context Protocol server that extracts and processes content from PDF documents, providing text extraction, metadata retrieval, page-level processing, and PDF validation capabilities.41
- AlicenseAqualityCmaintenanceA Model Context Protocol server that enables the extraction of text, metadata, and embedded images from PDF files. It provides tools for searching text with context, reading specific pages, and counting total pages within a document.7301MIT
- Alicense-qualityDmaintenanceA high-performance Model Context Protocol server that enables AI agents to extract text, images, and metadata from PDF documents using parallel processing. It features intelligent Y-coordinate content ordering to preserve natural reading flow and supports both local files and URL-based sources.17MIT
- AlicenseAqualityAmaintenanceA Model Context Protocol server that enables AI agents to read, search, and extract content from PDF files.13111MIT
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
Generate PDFs from templates via AI chat. Works with Claude, ChatGPT, Cursor, and any MCP client.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/MichaelLevinson/mcp_pdf_processor'
If you have feedback or need assistance with the MCP directory API, please join our Discord server