OCR MCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
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).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Screenshot any URL/HTML as PNG/JPEG/WebP, or read it as clean Markdown/text for LLMs.
Web tools for AI agents: URL to clean Markdown, site crawl, screenshots, PDF/Office to text, OCR.
Agent tools: clean web screenshots/PDFs, PDF & image OCR to Markdown, PageSpeed audits, email checks
Documents to Markdown/PDF, OCR, video and audio transcripts, TTS, screenshots, domains, frames.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceScrapes webpages and converts them to clean Markdown using browser automation, ideal for creating READMEs, documentation, or processing dynamic web content.MIT
- AlicenseAqualityDmaintenanceConverts URLs and raw HTML to clean Markdown, enabling AI assistants to read web pages for summarization, analysis, or ingestion.28 npm1MIT
- FlicenseNot gradedqualityDmaintenanceProvides OCR (Optical Character Recognition) capabilities through MCP, including text extraction and document layout parsing to Markdown. Supports multiple PaddleOCR models like PP-OCRv5, PP-OCRv6, and PP-StructureV3.-
- AlicenseAqualityCmaintenanceEnables AI agents to convert images and PDFs, including large scanned books, into Markdown through GLM-OCR, with support for long-image slicing, progress tracking, and asynchronous OCR tasks.71MIT