MCP CheckOCR & vision MCP servers
36 listed servers in AI & media generation. Each row shows the automated checks, the secrets asked for and an install command.
No keys needed, every check passed
OCR & vision servers 36
Now showing are unlisted. These entries didn't pass our listing filter: no source repo, a very short or duplicated description, or a publisher with 100+ servers. Same automated checks, shown as-is. How we check
| Type | Secrets | Version | Actions | ||||
|---|---|---|---|---|---|---|---|
★ 121 io.github.docling-project/docling-rs Documents to Markdown for agents: PDF layout, tables and OCR, Office, HTML, scans. docling in Rust. | 7/7All passed | 81health of 100 | PyPIRuns locally | Noneno keys asked | 2.52.9 | ||
★ 5 io.github.ellmos-ai/ellmos-filecommander-mcp Filesystem MCP server: files, previews, search, processes, OCR, archives, safe delete, web fetch. | 7/7All passed | 65health of 100 | npmRuns locally | Noneno keys asked | 1.11.4 | ||
★ 14 io.github.dimitar-radenkov/pointframe-mcp Windows screenshots, OCR, and redacted screen recording for AI agents. No desktop app needed. | 3/41 warning | 52health of 100 | MCPBRuns locally | Noneno keys asked | 6.7.163 | ||
★ 1 io.github.atabekdemurtaza/papyrio-mcp Compress, convert, merge, split and OCR PDFs from an assistant, using local files. | 7/7All passed | 52health of 100 | npmRuns locally | 1secret asked | 0.1.4 | ||
★ 9 io.github.pdfdotco/pdfco-mcp Official PDF.co MCP server: convert, merge, split, OCR, search and fill PDFs through the PDF.co API | 7/7All passed | 61health of 100 | PyPIRuns locally | 1secret asked | 0.0.11 | ||
★ 1 io.github.emanueld92/bug2context Turn bug screen recordings into chronological context for AI agents: frames, OCR, logcat, voice. | 7/7All passed | 59health of 100 | PyPIRuns locally | Noneno keys asked | 0.1.1 | ||
★ 4 io.github.mutonby/aikount-mcp Contabilidad española con IA: facturas, gastos por OCR, conciliación bancaria e impuestos AEAT. | 8/8All passed | 52health of 100 | PyPILocal or hosted | 1secret asked | 0.2.0 | ||
★ 1 io.github.JeenyJAI/mcp-test-utils Desktop UI automation for AI agents: verified clicks, UI Automation, OCR, scenario runs, recording | 4/4All passed | 52health of 100 | MCPBRuns locally | Noneno keys asked | 3.27.23 | ||
io.github.suparse/suparse-mcp Extract data, create schemas, and export results from PDFs and documents with Suparse AI OCR. | 7/7All passed | 54health of 100 | npmRuns locally | 1secret asked | 1.5.0 | ||
★ 7 io.github.alphaparkinc/genpark-hybrid-bounding-box-ocr-table-reconstructor-skill Spatial clustering 2D grid reconstructor converting OCR boxes into Markdown tables | 5/61 warning | 50health of 100 | MCPBRuns locally | Noneno keys asked | 1.0.1 | ||
★ 5 io.github.yrangana/fm-mcp Delegate summarising, extraction, classification and OCR to the macOS 27 on-device model. | 3/41 warning | 46health of 100 | CargoRuns locally | Noneno keys asked | 0.1.3 | ||
★ 10 io.github.Zeptap/zeptap Operate a real iPhone from a Mac: screenshots, OCR, taps, typing, opening apps. Needs Zeptap. | 7/7All passed | 53health of 100 | npmRuns locally | Noneno keys asked | 1.0.1 | ||
★ 1 io.github.sezzlee/pdf Extract text from local PDF documents with optional pluggable OCR. Read-only, no network. | 7/7All passed | 51health of 100 | npmRuns locally | Noneno keys asked | 0.1.2 | ||
★ 94 io.github.ParthibanRajasekaran/rendercheck Check from a screenshot that text is really visible to users. Local, offline OCR. | 7/7All passed | 69health of 100 | npmRuns locally | Noneno keys asked | 0.6.0 | ||
io.github.fernandoguiraud16-coder/pdf-text-extractor Extract text, pages and metadata from PDFs in bulk, with OCR for scanned files. | 3/3All passed | 43health of 100 | RemoteHosted | Noneno keys asked | 1.0.0 | ||
io.github.fernandoguiraud16-coder/document-to-markdown-tables Convert PDF, Word, Excel and scanned documents to Markdown, tables and RAG chunks. OCR. | 3/3All passed | 43health of 100 | RemoteHosted | Noneno keys asked | 1.0.0 | ||
 ru.smartpdf/smartpdf 24 PDF tools: convert to and from Office and JPG, compress, merge, split, OCR, sign, watermark | 4/4All passed | 43health of 100 | RemoteHosted | Noneno keys asked | 1.0.0 | ||
★ 2 io.github.lazyants/transkribus Transkribus REST and Processing APIs — collections, HTR/OCR; default v1, optional v2 beta. | 7/81 warning | 64health of 100 | npmRuns locally | 3secrets asked | 4.1.0 | ||
★ 162 io.github.jztan/pdf-mcp Agentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR. | 3/41 warning | 77health of 100 | PyPIRuns locally | Noneno keys asked | 3.5.0 | ||
★ 17 io.github.ostapondo/plonk Plonk gives agents local macOS tools for windows, workspaces, screenshots, OCR, and more. | 7/7All passed | 64health of 100 | npmRuns locally | Noneno keys asked | 0.4.3 | ||
★ 6 io.github.Xeakaes/computer-use-for-all-agents Safety-gated computer use for AI agents: screen OCR and vision, mouse, keyboard, window control. | 2/2All passed | 60health of 100 | RemoteRuns locally | Noneno keys asked | 1.0.0 | ||
★ 1 io.github.benbergner/benspdf Read PDFs locally: text, pages, metadata, scan detection, layout, permissions, render, OCR. | 7/7All passed | 55health of 100 | PyPIRuns locally | Noneno keys asked | 0.3.0 | ||
★ 5 io.github.elpabloultron/open-legal-chile Suite de Inteligencia Jurídica y 55 herramientas MCP para Chile: BCN, PJUD, doctrina y OCR. | 6/71 warning | 60health of 100 | PyPIRuns locally | Noneno keys asked | 1.5.1 | ||
 io.github.AgewellEPM/tinkyvision Screen observation, OCR and permission-controlled app input over MCP for Apple silicon Macs. | 5/61 warning | 41health of 100 | MCPBRuns locally | Noneno keys asked | 0.2.0 | ||
com.diemdesk/mcp Convert Office files and PDFs, OCR a scan, or capture a web page — from your assistant. | 7/7All passed | 59health of 100 | npmRuns locally | 1secret asked | 0.1.2 | ||
 ★ 8 io.github.woladi/macos-vision-mcp Local OCR & screen understanding for agents: read any window, find what to click. No uploads. | 7/7All passed | 59health of 100 | npmRuns locally | Noneno keys asked | 0.7.0 | ||
★ 21 io.github.wavyrai/rm-mcp Access your reMarkable tablet - read documents, browse files, extract text and OCR handwritten notes | 6/71 warning | 53health of 100 | PyPIRuns locally | 1secret asked | 0.7.0 | ||
★ 2 io.github.q1023884985/visiongemma Local AI vision MCP server for Windows: OCR, chart analysis, scene description. 100% offline. | 7/7All passed | 54health of 100 | PyPIRuns locally | Noneno keys asked | 2.1.0 | ||
io.github.xyun1996/ocular Vision tools for coding agents: screenshots, OCR, UI diffs, errors, tables, and charts. | 7/7All passed | 55health of 100 | npmRuns locally | 1secret asked | 0.1.0 | ||
★ 19 io.github.ARAS-Workspace/claude-kvm MCP server — control remote desktops via VNC with a native Swift daemon and Apple Vision OCR | 7/7All passed | 49health of 100 | npmRuns locally | 2secrets asked | 2.0.12 | ||
★ 3 io.github.ObscuritySRL/umbriel See and drive a whole Windows machine from Bun — apps, input, screen, OCR, registry, OS — via MCP. | 7/7All passed | 55health of 100 | npmRuns locally | Noneno keys asked | 1.14.0 | ||
| 7/7All passed | 51health of 100 | PyPIRuns locally | Noneno keys asked | 1.0.2 | |||
★ 1 io.github.EigenCharlie/pdf-toolkit-mcp Unofficial PDF toolkit (merge/split/compress/OCR/convert/watermark/protect/...) via iLoveAPI. | 7/7All passed | 41health of 100 | npmRuns locally | 2secrets asked | 0.1.2 | ||
★ 3 io.github.praveensehgal/remarkable Read, write, and manage your reMarkable tablet — browse, upload, create folders, move, delete, OCR | 7/7All passed | 44health of 100 | PyPIRuns locally | 1secret asked | 0.2.3 | ||
★ 1 io.github.ArkNill/docpick Schema-driven document extraction with local OCR + LLM. Document in, Structured JSON out. | 7/7All passed | 40health of 100 | PyPIRuns locally | Noneno keys asked | 0.1.2 | ||
★ 5 io.github.lukisch/bach-filecommander-mcp 43 tools for filesystem, process management, sessions, search, OCR, ZIP, and PDF export. | 7/7All passed | 63health of 100 | npmRuns locally | Noneno keys asked | 1.7.0 |
Showing 1 to 36 of 36