MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
An MCP (Model Context Protocol) server specialized in deciphering PDF internal structures.
npm MIT ★ 2 -
MCP server for PDF structure analysis - read, inspect, and validate PDF internals
npm MIT -
MCP server for efficient PDF text extraction, search, and metadata retrieval for Claude Code
npm MIT -
MCP server for efficient PDF text extraction, search, and metadata retrieval for Claude Code
npm MIT -
mcp-documents-readergithub.com/xt765/mcp_documents_readerupdated this year
An MCP enabled multi-format document reader supporting DOCX, PDF, TXT, and Excel files
pypi mit -
Local-first PDF reader for researchers: notes anchored to the page, AI answers that cite it. Runs offline with Ollama.
Apache-2.0 ★ 12 -
A PDF reader, CLI and MCP server that run on your computer: tables, charts, headings and scans to Markdown, HTML or JSON.
npm Apache-2.0 -
FixMyScan remote MCP server and agent skill: turn scanned books into clean, searchable PDFs for e-readers
MIT -
Local-first, zero-key web search MCP server: ddgs multi-engine + semantic search, reader-mode fetch, PDF, sqlite cache, GitHub search
MIT ★ 1 -
Universal MCP server for extracting text from various document formats and converts to .md file
MIT ★ 3 -
Local, token-efficient MCP server for evidence-first reading of PDF, DOCX, PPT, and PPTX research documents.
★ 2 -
Reads web pages and PDFs as clean Markdown: main content, the sections that answer a query.
MIT ★ 1 -
arxiv-reader-mcpgithub.com/YounesBensafia/arxiv-reader-mcpupdated this year
Want to search arXiv papers, fetch metadata, and extract full-text PDFs without leaving your editor? This MCP server connects any MCP-compatible client (Claude Code, etc.) directly to arXiv.
MIT ★ 25 -
Ask huge PDFs, Word documents and spreadsheets specific questions: your AI gets only the passages that answer, with citations. A local MCP server for Claude Code, Cursor and Codex, plus a browser version.
npm Apache-2.0 -
auto-reader-ocrgithub.com/Samqra/auto-reader-ocrupdated this year
Arabic-first OCR, translation & document extraction API — MCP server for Claude Code & agents. Keyless: first call mints a free trial key.
MIT -
Read the same book with your AI. A collaborative reader with text-anchored two-color highlights and an MCP server so an AI companion can flip through, mark up, and comment alongside you.
NOASSERTION ★ 47 -
Read QR codes and barcodes from images and PDF pages, offline, with JSON output
Apache-2.0 -
ATBgithub.com/Aniyra/ATBactive
面向 AI Agent 的全格式文件读取工具箱：统一解析 PDF/Office/图片/视频/压缩包/数据库，内置 MCP Server 与视频抽帧理解
MIT -
Model Context Protocol (MCP) server exposes tools to read multiple document types including DOCX, PDF, Excel, and TXT. This has been tested on Trae Desktop.
MIT ★ 23 -
antiquarIOgithub.com/JCarrascoF/antiquarIOupdated this year
A privacy first (local) document parsing tool and MCP server — convert PDFs and images to structured Markdown using multiple selectable OCR engines. Includes Streamlit GUI and hierarchical chunking for RAG workflows.
MIT -
MCP server that gives Claude OCR: read receipts, invoices and scanned PDFs, extract structured fields, and search your scans. Runs locally with Tesseract.
-
Free, private, offline file viewer for Windows: PDF, Word, Excel, PowerPoint, images, video and code. Open documents from Claude Code and request changes from inside the app.
MIT -
Self-hosted web scraper, crawler and document parser for AI agents: URLs, PDFs with OCR and Office files to clean Markdown/JSON. Firecrawl- and Jina-compatible API, MCP server, agent endpoint, Python/Node SDKs. Single Rust binary.
npm Apache-2.0 ★ 274