MCP servers tagged ocr
242 live MCP servers tagged "ocr", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with ocr.
Pdfvision
CLI, MCP server, and TypeScript library that extracts text, layout, and page images from PDFs for AI agents — when extraction goes wrong, it says so per page and says what to do n…
ReadMD
本地优先的全平台 Markdown 阅读器与编辑器：长文档语义分页、显示层非破坏纠错、Office/PDF/网页转 MD、离线 OCR、LaTeX 学术增强与 MCP 接入。爱发电：https://ifdian.net/a/natsummerance
eKYC Suite
KYC MCP server, eKYC MCP server, and KYC onboarding MCP for AI agents: identity verification, digital identity verification, selfie verification, face liveness, ID card OCR, docum…
Enquire
The most advanced MCP server for Obsidian vaults. Hybrid retrieval (BM25 + TF-IDF + multilingual ML embeddings, RRF-fused) with BGE cross-encoder reranking, HNSW vector index, int…
Media Pipeline MCP Server
MCP server exposing 30+ media operations via StreamableHTTP — provider routing, cost tracking, pipeline execution
Image Processor
MCP server for downloading, compressing, optimizing images, OCR text extraction, and batch processing with auto-generated reports. Supports WebP, AVIF, JPEG, PNG, and more.
Statementedge MCP Server
Model Context Protocol server for StatementEdge — convert PDF bank statements directly from Claude Desktop, Claude Code, or any MCP-aware client.
Pylon
Pylon AI — Pay-per-request APIs for the agent economy. Powered by x402 micropayments on Base.
Rust ReadMD
100% 纯 Rust 原生全平台 Markdown 阅读器与编辑器：长文档语义分页、显示层非破坏纠错、Office/PDF/网页转 MD、离线 OCR、LaTeX 学术增强与 MCP 接入。官网地址：https://rust.readmd.asia ； 爱发电：https://ifdian.net/a/natsummerance
Social Knowledge Base
Turn social-media creators' videos into a searchable, curated knowledge base — Next.js download/manage app + GPU transcription (faster-whisper) + RAG
Mistral Ocr MCP
MCP Server Showcasing How to Use mistral Document OCR functionality
Orbination AI Desktop Vision Control
Enable AI to interact with Windows apps by viewing screens, reading UI, clicking, typing, and automating tasks with OCR and window detection.
DeepLaw
DeepLaw 2.0：本地优先单用户 Agent Knowledge OS，融合自主长期记忆、Markdown-native 知识、可信 Ledger、有界上下文与可验证法律证据。
Pi Vision Struct
⛔ 已停止维护（EOL 2026-09-13，仓库只读）· Deprecated & archived：给纯文本模型的数理化视觉通道 + GUI 控制；已被 DeepSeek-V4.1 原生多模态取代。Numeric-grade vision channel + GUI control for text-only models — superseded b…
Evb Viewer
Scanned-document workbench that AI agents can operate: clean, OCR, annotate PDF and DjVu, with a local MCP server. macOS, Windows, Linux, Web.
Picture Identification MCP
本地视觉理解 MCP 服务，为 AI agent 提供识图能力：通过 vision / ocr / list_models / providers 四个 MCP 工具描述截图、界面、图表与照片。
Videolens
Universal video intelligence: turn any video + a prompt into a timestamped timeline, evidence-grounded findings, and structured reports — ready for AI agents.
Orbination AI Desktop Vision Control
Enable AI to interact with Windows apps by viewing screens, reading UI, clicking, typing, and automating tasks with OCR and window detection.
Docpick
Lightweight OCR + Local LLM → Schema-based Structured JSON Extraction
Question Bank Template
Self-hosted MinerU to WeKnora pipeline for parent, child, and raw question-bank retrieval, with read-only ChatGPT MCP access
Synorive
Search your files by meaning and fact-check the web, fully offline.
Macos Computer Use Kit
AX-first computer use for AI agents on macOS with optional Jev (TypeSafe System One) semantic guards: calibrated target/input judgments before an irreversible action, decisions ke…
Gather
Research intake that reaches the hard places: web, video, papers, scanned PDFs, browser, OCR, and audio into structured research packets. DOM extraction and change tracking built…
Local Multimodal Infra
Local multimodal inference service
Sorana
Personal AI Knowledge Workspacee
Impossible Ocr
A self-hosted OCR server that turns PNG and JPEG images into structured text using local PP-OCRv5 models through HTTP, gRPC and MCP.
Auto Mouse
Windows desktop UI context picker for AI agents: select windows, UI elements, or screen regions with hover highlighting, UI Automation, screenshots, local OCR, and user-approved M…
Shoucang
合订本 (HedingBen) — 专治收藏夹吃灰：把小红书笔记装订成本地可搜索合集。拖拽导入 · 本地 OCR · 语义搜索 · 全程离线。Tauri 2 + Next.js 16 + Chrome 扩展。
Dsh Vision
给 DeepSeek Harness（dsh 插件）与 Claude Code（MCP）提供视觉能力：本地 OCR（macOS / Windows）+ 云端 VLM（多供应商，OpenAI 兼容）
Video Context MCP
Local-first MCP server that turns video into queryable context with transcripts, keyframes, OCR, and semantic search.
Media2md
Turn images into structured, searchable markdown with AI vision
Hermes Document Reader
Hermes document reader plugin with OCR and document-processing service.
Screen Context Agent
Local screen history with OS-native OCR, encrypted storage and a read-only MCP server for any AI assistant (macOS; Windows beta)
Carrel
Read, index, pack and file your documents — from the terminal, for you and your agents.
Desk MCP
Windows desktop automation MCP server - screenshots, OCR, mouse and keyboard, and accessibility trees via UI Automation, MSAA and Chrome DevTools Protocol. Node.js + built-in Powe…
NovaBAIC
BetterAIChat2 (BAIC2) — 本地优先的 Android AI 智能体：流式聊天、Agents、52 个设备工具（截屏 OCR / UI 自动化 / 文件 / 网页 / 提醒 / 自动化 / 技能 / 子代理）、仿生记忆、MCP。Local-first Android AI agent with real device control.…
Images Dataset Studio
Local-first image dataset curation studio for inspection, annotation, OCR, PII detection, embeddings, segmentation, COCO, YOLO, exports, MCP, and modular AI plugins.
Tome
Agent-native knowledge OS: turn messy PDFs, scans & DOCX into a verifiable, Markdown knowledge base that LLMs & AI agents read, search and curate — over REST, MCP and a React Libr…
VideoXAgent
Online Video Agent Harness for Long Video Understanding.
Deepseek Harness
Local-first, safety-gated CLI and MCP harness for bounded DeepSeek batch and corpus workloads.
Screen MCP
Linux Wayland computer-use MCP for Claude Code & Grok — screenshot, click, type any desktop app.
backscroll
Local, searchable memory of your screen, queryable by Claude via MCP. Open-source, zero-dependency, macOS-first alternative to Screenpipe.
Iris MCP
High-precision Windows desktop control for AI agents via MCP. Three rendering backends (Win32 + UIA + OCR), Per-Monitor V2 DPI, SendInput + UIA Invoke clicks, live accuracy bench.
Manhua
An open-source, modular pipeline for translating manhua pages. Detect speech bubbles, extract text with OCR, translate using LLMs, and regenerate localized pages while preserving…
Pdf Library MCP
Persistent local library for mathematical PDFs: extract once with LaTeX, cache by content hash, search, and query over MCP. Greek and English.
Idpflow Core
Open-source MCP server for Intelligent Document Processing on LandingAI ADE. Ingest, classify, stack, and extract documents with page-level provenance and confidence. Works with C…
Markdown Everything
Privacy-first local context inbox for traceable Markdown, Obsidian vaults, and agents
DSH Plugins 4U
DSH 自建插件集合：微信桥接器 + GUI 微信入口补丁，一键安装
Class Schedule
原生 Android 课表：课程提醒、调休、桌面小组件、离线 OCR、OpenAI 导入与局域网 MCP；保留 Web/PWA。GPL-3.0-only。
Zen Vision
给纯文本模型（DeepSeek 等）装上眼睛：用 OpenCode Zen 免费多模态模型（mimo-v2.5-free）把图片转成文字描述。单文件、零成本、多源自动切换 + 实时视力监控。