OCR MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@OCR MCPRun OCR on this screenshot and return markdown."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
OCR MCP
MCP server che converte screenshot di pagine web in Markdown strutturato usando GLM-OCR (Zhipu). Si registra nel mcp-gateway: i tool compaiono in Claude come mcp__mcp-gateway__ocr__*.
Tool
Tool | Cosa fa |
| OCR di un'immagine già catturata. |
| Cattura uno screenshot full-page dell'URL con Chromium headless, poi OCR. |
| Stato e configurazione (host GLM-OCR, API style, modello, key, Chromium, tiling). Nessuna chiamata a pagamento. |
I tool restituiscono il Markdown come testo. Il server NON scrive file .md: gira su un LXC remoto senza accesso al disco locale. È la sessione Claude a salvare il .md dove serve (es. "salva il risultato in ./pagina.md").
Related MCP server: urltomarkdown-mcp
Motore OCR — .env
Il server è agnostico all'endpoint: si passa da cloud a self-hosted cambiando solo il .env.
Variabile | Cloud Zhipu | vLLM self-hosted |
|
|
|
|
|
|
|
|
|
| chiave API Zhipu | token del server vLLM |
chat→POST {BASE}/v1/chat/completions(OpenAI-compatibile).layout_parsing→POST {BASE}/layout_parsing(endpoint dedicato Zhipu).
Screenshot molto alti: tagliati in tile sovrapposte (MAX_TILE_HEIGHT / TILE_OVERLAP / MAX_TILES) e il Markdown viene ricucito automaticamente.
Deploy (CT102)
./deploy/install.sh root@192.168.1.107rsync → /opt/ocr-mcp, crea venv, playwright install --with-deps chromium, installa e avvia il servizio systemd ocr-mcp. Poi su CT102 compila /opt/ocr-mcp/.env e systemctl restart ocr-mcp.
Registrazione nel gateway
Su CT102, aggiungere alla lista upstreams: in /etc/mcp-gateway/upstreams.yaml:
- name: ocr
url: http://127.0.0.1:8011/sse
tags:
- core
- ocrpoi systemctl restart mcp-gateway.
Porta 8011: la 8009 è occupata da
gmaile la 8008 da un altro servizio. Se va cambiata, aggiornareconfig.py,.env,deploy/ocr-mcp.servicee la voceupstreams.yaml. Il tagcorerende i tool visibili nelle sessioni che caricano il set core del gateway.
Verifica
curl http://127.0.0.1:8011/→ 200 con stato.In Claude Code
/mcp→mcp__mcp-gateway__ocr__ocr_image | ocr_webpage | ocr_health.Chiamare
ocr_health, poiocr_webpagesu una pagina lunga reale.
Stack
Python 3.12 · FastMCP (mcp==1.27.0) · Uvicorn · httpx · Playwright/Chromium · Pillow. Transport SSE su /sse, servizio systemd, log di audit dei job in SQLite (/var/lib/ocr-mcp/ocr_mcp.db).
This server cannot be deployed
Maintenance
Related MCP Connectors
Screenshot any URL/HTML as PNG/JPEG/WebP, or read it as clean Markdown/text for LLMs.
Convert documents and web pages to clean Markdown: PDF, DOCX, XLSX, EPUB, scanned files, any URL.
Read a URL as clean markdown, screenshot a website, url to PDF. Web access for agents, no signup.
Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceScrapes webpages and converts them to clean Markdown using browser automation, ideal for creating READMEs, documentation, or processing dynamic web content.-
- AlicenseAqualityDmaintenanceConverts URLs and raw HTML to clean Markdown, enabling AI assistants to read web pages for summarization, analysis, or ingestion.24 npm1MIT
- AlicenseNot gradedqualityDmaintenanceConverts any webpage into clean, LLM-ready Markdown, removing noise and supporting JavaScript rendering.MIT
- AlicenseAqualityAmaintenanceConverts any web page URL into clean Markdown for LLM context (Claude, ChatGPT, etc.) with zero external API calls, running entirely locally.145 npmMIT