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.
Forgesyte
ForgeSyte is a modular AI‑vision MCP server
Chart Vision MCP
Local TradingView chart analysis via OpenCV + Tesseract OCR. No API keys, no GPU, runs fully offline — MCP server with color/level/zone detection.
Textbrowser
MCP server — text-first headless browser (DOM + OCR). Zero image tokens by default; 5-15x cheaper than screenshot-based browser MCPs.
Read4all
多格式附件提取 MCP Server — MinerU 优先 + 本地降级,PDF/Office/图片/网页文档 → Markdown。已发布 PyPI:uvx read4all
Lucida Vision MCP
通用视觉感知 MCP 服务器（眼睛不是大脑）/ General-purpose visual perception MCP server (eyes, not brain)
Pdf Toolbox MCP
Local-first PDF processing MCP server — OCR write-back, page surgery, encryption (OCRmyPDF + Poppler + qpdf)
Ocr Document Analysis Model Router
BYOK model router for OCR document analysis, invoice extraction, bank statement extraction, scanned PDFs, and long PDFs.
Hands On LLM
These are tests of technologies that serve RAG , OCR , VLM ,MAE ...
Local Vision
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.
Kagaz
Local-first document vault manager for macOS. Names, files and tags your documents by convention — no database, no cloud, no proprietary format. Agent-legible: --json everywhere,…
Documentpro MCP
Documentation for the DocumentPro MCP server — extract and classify structured data from invoices, POs, receipts, and tax forms with any MCP-compatible AI agent
Markitdown Zh Tw
MarkItDown（Microsoft，MIT）的非官方繁體中文教學站——把整個 repo（程式碼／轉換器／CLI／MCP／外掛／Azure）做成中英對照講解：概念地圖、學習路線、安裝指南、12 個文件教學頁、12 個程式碼對照頁，並收錄 markitdown 真實轉換輸出與 graphify 互動知識圖譜。
Nvidia Media MCP
MCP server exposing NVIDIA NIM media tools for image generation, OCR, and video understanding
Vzt Video Intel
The missing middle between raw video and reasoning models. Turn video into structured intelligence. Citable, queryable, AI-ready. CLI + MCP server. No Docker. No GPU.
WindownComputerUse
MCP server giving Claude (and other MCP clients) human-like control of Windows — virtual cursor, OCR, emergency stop, Electron manager. 64 tools.
AI Hands
Multi-layer desktop automation for AI agents — browser CDP, Windows UIA, vision/OCR. Successor to AIWander/hands.
MTA Plugin
Give any AI assistant a private, token-free memory of your files — Claude, Gemini, Cursor, VS Code, Windsurf, Codex & Grok. Converts attachments (PDF/Office/EPUB/archives) to Mark…
AI Agent MCP Tool For Multi Docu PDF PNG QR File Conversion Processing Capability
Free local-first MCP server giving AI agents private token, RAG, context, CSV/JSON and QR tools; PDF, OCR, DOCX and image processing roadmap. MIT by DJAI Academy & Siamese Cat Dev.
OpenControl
Give any AI real hands on a Windows PC. A single ~2 MB Rust MCP server with 54 native tools for seeing and controlling the desktop. No Python, no cloud.
Fax To Email
Fax-to-email API — open a 24h receive window, get faxes delivered to your inbox with optional OCR. Pay with Bitcoin Lightning, no subscription. MCP-native. Alternative to eFax, My…
Data Platform Servers
MCP servers enabling AI agents to interact with Pentaho PDI, Power BI, Oracle, and OCR engines
Pdf Rich MCP
Single-surface PDF intelligence MCP for Claude Desktop: LLM extraction, OCR, repair, true content-stripping redaction. Complements pdf-toolkit.
Universal File RAG
Hybrid RAG over PDFs, DOCX, spreadsheets, code repos, audio & images — explainable per-file retrieval routing (vector/hierarchical/code-graph), cited answers, and an MCP server. P…
Docintel MCP
Document Intelligence MCP server: extraction, confidence-threshold routing, human review queue, and BM25 search over the Model Context Protocol
Hirara
Self-hosted toolkit of tools for AI agents & LLMs — web search, PDF, OCR, Office, sandboxed code execution. Python SDK + MCP, no API keys.
Pdf2epub Paddle
📚 Convert scanned PDFs into clean EPUB ebooks effortlessly with intelligent layout analysis and smart chapter detection.
Deepvision Local MCP
本地识图 MCP：给 DeepSeek 等纯文本模型补看图能力（OCR/检测/分割/零样本，全本地）
Picturereader Zcode
ZCode plugin: pixel-to-text image reading for text-only models. image_scan / image_ocr / image_sample via MCP, plus the image-reading methodology skill. Port of the picturereader…
Glm4v Vision MCP
GLM-4.6V 图像理解 MCP：识图/OCR/图表解析，原生接入 DeepSeek Harness（dsh-mcp-client），也兼容 Codex/Cline 等
Comfyui LLM Partyy
LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,and adapts to all llms with similar openai…
OpenResponses
Apple-native SwiftUI developer playground for the OpenAI Responses API with streaming, tool calling, computer use, voice, OCR, MCP, and request inspection.
Local Document Parser MCP
Local-first DOCX/PDF/Excel parser with MCP, chapter/table extraction and macOS Vision OCR｜本地优先的文档解析与 MCP 工具
Wand
Agent-driven Apple Simulator automation (iOS · iPadOS · watchOS) — real gestures, accessibility + on-device OCR, and the watchOS Digital Crown. One dependency-free binary; CLI + M…
Superbased Claude Code Plugin
SuperBased plugin for Claude Code — screenshot capture, AI vision, OCR, screen recording, visual regression testing, token compression, voice dictation, and proactive monitoring v…
Knowledge Forge
Local-first AI knowledge base desktop app: PDF/DOCX/image ingestion, OCR, chunking, embedding, LanceDB vector search, MCP access, and optional AnythingLLM sync. Windows EXE packed.
Verifydoc
Trust layer for document→JSON extraction & AI agents: calibrated per-field confidence + source grounding + accept/review abstention on any OCR/VLM. Ships VerifyDocBench, a novel g…
Universal AI Converter
Agent-agnostic document, image, audio and video conversion to Markdown via CLI, Python, HTTP and MCP.
Clipmind
Local-first multimodal video evidence extraction for humans and AI agents. Paste a YouTube or Douyin link or drop a file; get transcript, OCR, visual states and a structured Evide…
CareAid AI
Built for The Infinity AI BuildFest 2026 by Team MindMatrix
SimulateInput
Cross-platform desktop and browser automation platform for testing websites, desktop apps, installers, and system UI flows.
Superbased Copilot Plugin
SuperBased plugin for GitHub Copilot CLI — screenshot capture, AI vision, OCR, screen recording, visual regression testing, token compression, voice dictation, and proactive monit…
Superbased Cursor Plugin
SuperBased plugin for Cursor — screenshot capture, AI vision, OCR, screen recording, visual regression testing, token compression, voice dictation, and proactive monitoring via 28…
Erasetext API
Official docs, OpenAPI, MCP, Python SDK, LangChain and LlamaIndex tools for the EraseText API
Ezdxf MCP
Noncommercial visual web research, image-to-DXF, spatial recognition, and exact Cartesian targeting engine
Aimorsel
本地运行的文档结构化提取工具：PDF / Word / Excel / PPT / 网页 / 图片 → Markdown、JSON、HTML、纯文本。全程离线，文件不出本机。
Incident Zero Multimodal Agentic Security Platform
An end-to-end agentic pipeline that accepts code repositories, log files, screenshots, and architecture diagrams, runs specialized MCP (Model Context Protocol) security tools, cor…
Tuttikit
自己跑、自己改、自己说了算的简易多 Agent 框架 · Conductor + Sub-agents · Skills + MCP · 多设备同步
Readur MCP
An MCP server for interacting with a Readur instance
Dsh Vision Primitives
Native interactive visual-reasoning plugin for DeepSeek Harness: precise pixel grounding (SOM grid / zoom / annotate / measure / diff / color / OCR) + MiMo V2.5 multimodal backend…
Healthcare Redaction MCP
Scalable engine for detecting and redacting PHI/PII from healthcare documents and data streams. Supports OCR and NLP-based extraction, configurable redaction rules, audit logging,…