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.
-
MCP server for OCR using native Tesseract (C++), built with Node.js, delivering up to 10x faster performance than tesseract.js and integrable with ChatGPT Desktop.
MIT ★ 11 -
MCP server that gives Claude OCR: read receipts, invoices and scanned PDFs, extract structured fields, and search your scans. Runs locally with Tesseract.
-
OCR in the browser and Node.js with the tesseract.js API: PP-OCRv6-Small on LiteRT.js (WebGPU or WebAssembly), images never leave the device. PDFs, scans and photos to Markdown with tables, JSON or text; a CLI and an MCP server.
npm Apache-2.0 -
MCP server: OCR for photographed and scanned Bulgarian documents. Tesseract + OpenCV, per-page confidence, vision fallback only for weak pages, sandboxed to allowed folders.
MIT -
Kurage OCR Work — OCRエンジン(PaddleOCR・Tesseract・Docling・生成AI)を切り替えて注文書を読み比べ、受注登録まで。画面・API・MCP
MIT ★ 1 -
Multi-engine OCR MCP server (RapidOCR + Tesseract + ABBYY FineReader 16) with per-line confidence, engine comparison, and CER/WER accuracy evaluation. Local/headless, Windows-first.
MIT ★ 1 -
Local-first OCR gateway inspired by FreeLLMAPI. Built-in Tesseract, cloud and self-hosted adapters, web, Windows desktop, CLI and MCP.
MIT -
Local OCR with Tesseract: turn scans and photos into searchable PDFs on your own computer. Page editing and an MCP server for AI assistants. Linux · Windows · macOS · EN/ES
Apache-2.0 ★ 1 -
chart-vision-mcpgithub.com/nessos666/chart-vision-mcpupdated this year
Local TradingView chart analysis via OpenCV + Tesseract OCR. No API keys, no GPU, runs fully offline — MCP server with color/level/zone detection.
MIT ★ 3 -
MCP Server for tesseract
MIT -
Scanned documents, read every word with its box and its confidence.
MIT ★ 2 -
homepilotgithub.com/orcunku/homepilotupdated this year
AI home assistant with OCR, RAG, and MCP
-
👓 Computer vision–based automation tool for remotely controlling Android devices via Go server and custom client.
Apache-2.0 ★ 2 -
MCP server for reading and analyzing images with OCR and AI vision capabilities
pypi MIT -
pdf-tools-mcpstale
PDF Tools MCP server with OCR capabilities - Convert PDFs to images, extract text with OCR, extract images, and metadata
npm MIT -
visual-window-controlgithub.com/sunasaji/visual-window-controlupdated this year
MCP server & CLI for controlling windows visually — capture screenshots, OCR text extraction, and keyboard/mouse input
pypi MIT -
Turn images into structured information for AI agents. OCR, image understanding, colours, layout, CLI and MCP.
Apache-2.0 -
OmniPDF Studio - Suíte completa de PDF com TrueEdit, IA, OCR e ferramentas offline
MIT -
Local PDF text extraction in the browser and via MCP, with English/German OCR, page-level paragraphs, and basic table readability.
npm MIT -
Search engine over Twitter screenshots. OCR ingest, full-text and semantic search, topic clustering, and MCP server for LLM integration.
★ 1 -
AI-powered document perception and analysis MCP server with intelligent provider selection
pypi Apache-2.0 -
recipe-toolsgithub.com/lka/recipe-toolsupdated this year
MCP server for extracting recipes from PDFs or jpegs into structured HTML using OCR and LLM-assisted interpretation.
MIT -
@sin-gang-ya-rou-geng-hao-chih/pdf-mcp-servergithub.com/j0482k6j041/pdf-mcp-serverupdated this year
Model Context Protocol (MCP) server for PDF processing with OCR support
npm ISC -
SUMIPDF - local-first PDF editor: true redaction, text replacement, OCR, AES-256, page ops, sanitize. MIT. MCP server built-in.
MIT -
MCP server for comprehensive PDF processing with 18 specialized tools
pypi MIT -
Lightweight, ultra-fast FastMCP server for Computer Use & GUI automation on Linux and Windows (Mouse, Keyboard, OCR, Video, Web).
MIT ★ 5 -
Privacy-first, self-hosted PDF toolkit with a built-in MCP server. Merge, compress, and OCR documents (including Russian) through a web UI or AI agents. One Docker container.
MIT -
Rules-based engine that turns bank statements and mobile money exports (PDF, scanned PDF/OCR, CSV, TSV, XLSX) into normalized, accounting-checked JSON transactions. CLI, REST API, MCP server, Python SDK. French, European and UEMOA formats. 120 tests. MIT.
MIT -
PRIVIO SENTRY - tarja de CPFs, endereços e outros dados pessoais em PDFs com IA local (Tesseract + YOLO + servidor de IA pela API), revisão humana num editor web, API e servidor MCP para agentes, verificação pós-tarja que falha fechado. Apoia práticas alinhadas à LGPD; não garante anonimização. Projeto pessoal e open source (AGPL-3.0).
AGPL-3.0 ★ 8