PDF MCP Servers

Find MCP servers for PDF parsing, document extraction, OCR, conversion, summarization, and agent workflows around files.

对比服务器搜索 PDF

匹配的 MCP 服务器

结果来自现有 MCP Servers 目录，没有单独的主题数据库。

查看所有搜索结果
PDF2MD.node (mcp-node.io)
Privacy-first PDF to Markdown/JSON converter for AI Agents. Optimized for complex B2B invoices (E-Fatura) and tables. Features native Turkish character correction and local-first WASM parsing.
查看服务器
PDF Agent MCP
A server for AI agents to selectively process and extract content from PDF documents.
查看服务器
PDFCheck MCP
View PDF metadata, detect AI-generated content, check edit history & verify authenticity.
查看服务器
PDF.co MCP
Perform various PDF processing tasks using the PDF.co API.
查看服务器
PDF MCP Server
Extract text and data from PDF files using pdfplumber by providing local file paths.
查看服务器
PDF Toolkit MCP
Create PDFs from Markdown, fill forms, merge, split, rotate, watermark, encrypt, extract text, and add QR codes. 16 tools, TypeScript-native.
查看服务器
Custom PDF MCP Server
A server for processing PDF files, allowing text and table extraction, metadata retrieval, and file listing within a specific directory.
查看服务器
Excel to PDF MCP Server
Convert Excel and Apple Numbers files to PDF format.
查看服务器
Stimulsoft Documentation MCP Server
官方
Official MCP server for Stimulsoft Reports & Dashboards documentation. Semantic search across FAQ, Programming Manual, Server/User Manual, and Server/Cloud API for .NET, WPF, Avalonia, WEB, Blazor, Angular, React, JS, PHP, Java, and Python platforms.
查看服务器
Document Evaluation MCP Server
Evaluates technical documentation against globalization standards, analyzing for translation issues, ambiguity, and sentence length.
查看服务器
Document Extractor MCP Server
Extracts document content from Microsoft Learn and GitHub URLs and stores it in PocketBase for retrieval and search.
查看服务器
document-generator-mcp
generate pdf and word
查看服务器

PDF MCP 适合的场景

Let agents extract text, tables, metadata, and citations from PDFs before summarizing or answering.

Convert documents into markdown or structured data for RAG, research, and knowledge-base workflows.

Handle document-heavy operations without manually copying file content into prompts.

设置清单

  1. 1Choose a PDF server based on parsing quality, OCR needs, table support, and accepted file sources.
  2. 2Scope file access to the relevant folder, workspace, or upload flow.
  3. 3Add the server command and file permissions to your MCP client configuration.
  4. 4Test with a representative PDF and confirm extraction preserves page references or useful metadata.

如何选择

  • Check support for scanned PDFs, tables, images, page ranges, and output formats.
  • Prefer servers that preserve source filenames, page numbers, and extraction confidence where available.
  • Keep sensitive documents local or read-only unless your workflow explicitly requires uploads.

PDF MCP 常见问题

What is PDF MCP used for?

PDF MCP gives agents tools for reading, extracting, converting, and summarizing PDF documents through the Model Context Protocol.

How is PDF MCP different from general document processing MCP?

PDF MCP targets the highest-intent document keyword directly. Broader document processing can include DOCX, OCR, conversion, and extraction around the PDF workflow.

Can PDF MCP read scanned documents?

Only if the server includes OCR or delegates to an OCR service. Check scanned-PDF support before relying on it for forms or image-heavy documents.