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.
-
Papely — Generate personalized PDFs in bulk from your own PDF template. CSV/Excel data, email delivery with per-recipient tracking, public REST API and MCP server.
-
Self-hosted document conversion and image rendering API — DOCX/XLSX/PPTX to PDF, HTML to PDF, PDF merge, and HTML templates to PNG. Gotenberg with API keys, quotas and usage metering built in. Also an MCP server.
MIT -
mcp-pdf-utilsgithub.com/zekovdev/mcp-pdf-utilsupdated this year
MCP server for PDF manipulation — merge, split, rotate, extract, watermark. Zero API keys, fully offline.
MIT -
Extract tables from PDFs into CSV. Free local CLI and MCP server. No API key.
MIT -
pdf-toolkit-mcpgithub.com/eigencharlie/pdf-toolkit-mcpupdated this year
Unofficial MCP server exposing PDF operations (merge, split, compress, OCR, convert, watermark, protect, and more) via the iLoveAPI REST API. Not affiliated with iLovePDF SL.
npm MIT -
mcp-pdf-utilsupdated this year
Local MCP server for PDF manipulation — merge, split, rotate, extract, watermark, metadata. Zero API keys, fully offline. Works with Claude, Cursor, ChatGPT.
npm MIT -
Free online: Markdown → typeset PDF and editable Word; Word, LaTeX and PDF → Markdown. Correct Chinese text. MCP server and HTTP API, no sign-up. Feedback welcome.
-
invovate-mcp-servergithub.com/LightSpeedPlusOne/invovate-mcp-serverupdated this year
MCP server for the Invovate invoice API — generate PDF, JSON & UBL 2.1 invoices in 11 languages from AI agents (Claude Desktop, Cursor, Windsurf).
MIT ★ 1 -
pdf-toolkit-mcpgithub.com/EigenCharlie/pdf-toolkit-mcpupdated this year
Unofficial MCP server exposing 18 PDF operations (merge, split, compress, OCR, convert, watermark, protect, ...) via the iLoveAPI REST API. Not affiliated with iLovePDF SL.
MIT ★ 1 -
superPDF AI on your computer: PDF tools for Terminal, scripts and AI agents (command-line tool, MCP server and local API)
npm Apache-2.0 -
Open-source screenshot & PDF API. Self-hosted alternative to ScreenshotOne and Urlbox. Playwright-based, blocks ads & cookie banners, full-page, caching, S3 upload, MCP server for AI agents. docker compose up.
★ 1 -
让 AI agent（Claude Desktop / Cursor / Cline / VS Code / Codex / dsh）调用本机打印机的 MCP server：HTML、网页、PDF、图片、批量打印，支持热敏小票与面单标签。覆盖 web-print-pdf 2.x 全部公开 API。
npm MIT -
MCP server for the Papyrio PDF API: compress, convert, merge, split and OCR PDFs from an assistant.
npm MIT -
Website audit, tech-stack detection, page-to-Markdown, broken links & PDF/OCR in one API. Sold via RapidAPI, x402 pay-per-call (USDC) and MCP.
GPL-3.0 -
Official MCP server of the Conv2pdf API: an AI assistant converts Office documents, images, e-books and web pages to PDF, and merges, splits, compresses, protects or converts the PDFs of your computer. Hosted in the EU (France).
npm MIT -
filetopdf-mcpupdated this year
Model Context Protocol (MCP) server for FileToPDF — convert files, HTML, and Markdown to PDF from any MCP client (Claude, Cursor, etc.). Bring your own API key.
npm MIT -
MCP server for per-customer PDF document management and RAG. Ingests text, scanned and chart-heavy PDFs (PyMuPDF + Tesseract + vision model), isolates each customer in its own Qdrant collection, and returns cited answers with deep links to the original PDF page. Local-first with Ollama, or any OpenAI-compatible API.
MIT -
Markdown in, PDF out, in any company's brand, detected live from its URL. One HTTP call, no API key. REST API + hosted MCP server.
MIT -
@templatefox/mcp-servergithub.com/templatefoxpdf/mcp-serverupdated this year
MCP server for TemplateFox PDF generation API - Generate PDFs from templates via AI assistants
npm MIT -
MCP server for the Screenshotty API: screenshots (returned inline to the assistant) and PDFs of any web page
MIT -
A Java-based server leveraging Apache Tika to extract content and metadata from files (PDF, DOCX, TXT, etc.) in a local files-to-extract directory. Supports HTML (with CSS styling) and text extraction, file listing, and metadata retrieval via MCP-compliant tools and REST APIs. Built with Spring Boot, Jetty, and MCP SDK.
-
rendershot-mcp-servergithub.com/Rendershot/rendershot-mcp-serverupdated this year
MCP server for the Rendershot screenshot & PDF generation API
MIT ★ 3 -
Document Suite: open-source PDF and image viewer and editor for React, Vue and Angular, with a REST API and an MCP server. Self-hosted and MIT licensed.
MIT -
mcpgithub.com/conv2pdf/mcpactive
Official MCP server for the Conv2pdf API: an AI assistant converts Office documents, images and e-books to PDF, and merges, compresses or protects the PDFs of your computer. Hosted in the EU (France).
npm MIT -
Zero-dependency MCP (Model Context Protocol) server for real-time Cloud GPU, Residential Proxy, Web Scraping API, HTML-to-PDF API, US LLC Formation, and SEO/iPaaS TCO calculation.
npm MIT -
mcp-parsekitgithub.com/cosmic-api/mcp-parsekitupdated this year
MCP server for ParseKit — document intelligence API for AI agents. Submit any PDF, image, or spreadsheet and get back clean, structured JSON.
npm MIT -
MCP server that converts Markdown to print-optimized A4 HTML (not a PDF: save as PDF via browser Ctrl+P). No API key required.
npm MIT -
Open-source API to convert URLs and documents into PDFs, screenshots, Markdown, and structured data.
AGPL-3.0 ★ 7 -
light-OCR-modulegithub.com/dwain-barnes/light-OCR-moduleupdated this year
Local OCR that turns scanned PDFs and images into clean Markdown — powered by LightOnOCR + llama.cpp. 100% on-device, no cloud, no API keys. Python library, CLI, MCP server, and Claude Code skill in one package
MIT -
MCP server for the Unfold API: PDF, DOCX, PPTX and XLSX documents to Markdown for AI agents.
MIT -
MCP server providing OCR capabilities to LLMs via Google Cloud Vision API - Read scanned PDFs, handwritten text, and images with any orientation
MIT ★ 1 -
MCP server for the InkRelay printing API: list printers, print PDFs, ZPL labels and ESC/POS receipts, and follow print jobs
npm MIT -
@fclwtt/anydoc-mcpactive
MCP server wrapping Firecrawl anydoc — convert documents (docx/pptx/xlsx/pdf/odt/rtf/epub/csv) to clean GitHub-Flavored Markdown. Pure local, no API key.
npm MIT -
mcp-local-visiongithub.com/jshsakura/mcp-local-visionupdated this year
Give text-only LLMs (GLM, DeepSeek, ...) eyes. MCP server that reads images and PDFs with a vision model on your own GPU — no API keys, nothing leaves the machine.
-
MCP server for Russian business paperwork: invoices with bank payment QR (GOST R 56042), acts of completed work, payment QR codes, amounts in words - PDF, fully local, no API keys
MIT -
Collects research material from web pages, papers, APIs, PDFs, scans, audio and video into a local corpus where every item records its source, method and hash.
pypi AGPL-3.0 ★ 5 -
MCP server + CLI that turns text, web pages and PDFs into interactive mind maps (Markdown outline → standalone markmap HTML). Zero API key required.
npm MIT -
Local AI resume & cover-letter builder: paste a job URL, get a tailored, truthfulness-guarded resume in four templates (PDF/HTML/ATS). Use the Anthropic API, or bring your own agent via MCP.
MIT ★ 5 -
MCP server that converts PDF, DOCX, PPTX, XLSX, HTML and EPUB documents — from a URL or base64 — into clean Markdown, with table extraction, full-text search and OCR for scanned files. No API key required.
pypi AGPL-3.0-or-later -
Open-source Reducto alternative: parse PDFs, scans and forms into Markdown, tables and typed data with a citation for every value. Claude Haiku or any model. Python library, MCP server, Reducto-compatible API.
Apache-2.0 -
Servidor MCP para estudar com IA: busca híbrida (texto exato + significado, local e sem chave de API) em anotações, PDFs e código, sempre citando a fonte; dúvidas, progresso e quizzes
npm ISC -
MCP server for Brazilian data and document tools: Pix BR Codes, CEP/CNPJ lookup, official Central Bank rates, web capture and PDF compression. Pay-per-call in USDC on Base via x402 — no signup, no API key.
npm MIT -
Syllabus-to-Study-Plan-MCP-Servergithub.com/Kangaeruhito14/Syllabus-to-Study-Plan-MCP-Serverupdated this year
MCP server: drop a syllabus PDF → get a day-by-day study plan with spaced repetition → export to ICS, Google Calendar, or Notion. Works in Cursor, VS Code, Claude Desktop, and Windsurf. No paid API required.
MIT -
Read papers as clean text: PDFs and scans become text you can read, translate and ask about, with notes and an agent that reads the pages and the web. MCP connector and REST API. Free to start, the model included.
MIT -
Web pages and PDFs to clean, LLM-ready Markdown as a remote MCP tool (Claude, Cursor, VS Code) and via the Apify API. Token counts, small crawls, sitemaps, RAG chunks, respects robots.txt. Python and Node examples.
MIT -
Pixo-Agentgithub.com/Kuddah/Pixo-Agentupdated this year
Pay-per-call image & PDF processing for AI agents — 21 operations over plain HTTP and native remote MCP, paid per request in USDC via x402 v2 on Base + Solana. No accounts, no API keys, files never stored. Public guide: quick start, MCP connection, pricing, payment flow.
-
screenshot-apigithub.com/raphy78626/screenshot-apiupdated this year
URL → PNG/JPEG/PDF capture API + MCP server for AI agents. Playwright + Fastify, deploy-ready on Fly.io.
MIT -
MCP server for the Notion API: pages, databases, views, native markdown, comments, and a full file pipeline with in-place PDF reading
MIT -
iteratools-mcpgithub.com/fredpsantos33/iteratools-mcpupdated this year
40+ pay-per-use API tools for AI agents via IteraTools — web search, image gen, TTS, QR code, PDF, browser automation and more
npm MIT -
Free self-hosted OCR & document data extraction API. Turn PDFs, scans, invoices, receipts & bank statements into JSON, CSV or Excel. No API keys, no cloud. Web UI, CLI, folder autopilot, MCP server.
MIT ★ 2 -
dws-mcp-serverno update data
Parse, convert, sign, redact, OCR, and extract structured data from PDFs and Office docs via the Nutrient DWS API
smithery -
@gridstorm/mcp-servergithub.com/007krcs/grid-dataupdated this year
GridStorm MCP server — tool definitions for Claude/LLM integration with grid and PDF APIs
npm MIT -
MCP server for the Google Slides API: create and edit presentations, slides, text, shapes, tables and images, speaker notes, export to PDF or PPTX
MIT ★ 1 -
iteratools-mcpgithub.com/fredpsantos33/iteratools-mcpupdated this year
MCP server for IteraTools API - text utilities, QR codes, PDF tools and more
-
Send real faxes from any MCP-enabled AI assistant. Wraps the FaxDrop API (PDF/DOCX/JPG/PNG, international numbers, status polling) with rate limits, dry-run mode, and audit logging.
npm MIT -
Send real faxes from any MCP-enabled AI assistant. Wraps the FaxDrop API (PDF/DOCX/JPG/PNG, international numbers, status polling) with rate limits, dry-run mode, and audit logging.
MIT ★ 5 -
Self-hosted MCP server and Tavily-compatible API for AI agents: web search, extract, crawl and map in one lightweight CPU-only Python process. JS pages via headless Chromium, PDF, no API keys.
AGPL-3.0 ★ 3 -
evernote-local-mcpgithub.com/nord342/evernote-local-mcpupdated this year
Read your Evernote v10+ notes from Claude (Desktop or Code) without an API key — local MCP server + CLI for macOS. Includes image OCR, PDF text extraction, and inline image viewing.
MIT ★ 1 -
MCP server + CLI that turns text, web pages and PDFs into interactive mind maps (Markdown outline → standalone markmap HTML). Zero API key required.
MIT -
Equalang Translationno update data
Translate PDF, Word (DOCX), Excel (XLSX), PowerPoint (PPTX), images, subtitles and text. Turn audio/video into transcripts or translated subtitles. Preserve document layout where supported. Requires an Equalang API key and credits.
smithery