Bridges local vision engines (Tesseract.js OCR and Sharp preprocessing) with Ollama vision models for image analysis, comparison, text localization, and browser screenshot annotation over MCP-compliant HTTP/SSE transports.
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
process.env. You'll be asked to provide them before it can run.CORS_ORIGINS— (empty = allow all) Comma-separated list of allowed CORS origins for the /upload endpoint.DOWNLOAD_DIR— ./tmp/hvm-downloads Directory for downloaded images from URLs (via download_image tool or transparent URL resolution).FEEDBACK_DIR— /tmp/hvm-feedback Directory for saved output images (annotations, diffs, overlays).MAX_DOWNLOAD_SIZE_MB— 50 Maximum download size in megabytes for URL-based image downloads.MAX_UPLOAD_SIZE_MB— 20 Maximum upload size in megabytes.MCP_REQUEST_TIMEOUT_MS— 300000 Timeout for MCP client request/response in milliseconds. Heavy vision tools may exceed the default 60s SDK timeout; set this to match or exceed OLLAMA_TIMEOUT_MS.MCP_SERVER_URLOLLAMA_HOST— Ollama running locally (or reachable via )OLLAMA_TIMEOUT_MS— 180000 Timeout for Ollama vision requests in milliseconds.PORT— 11402 Express listener port.UPLOAD_DIR— /tmp/hvm-uploads Directory for temporary binary image uploads.UPLOAD_RATE_LIMIT— 10 Maximum upload requests per minute per client IP.VISION_MODEL_FAST— llava:13b Default vision model for analyze_image and detect_ui_elements.VISION_MODEL_HEAVY— qwen3-vl:30b Default vision model for find_text_element, compare_images, browser_screenshot_analysis, visual_diff, and detect_ui_elements.[](https://m8ven.ai/mcp/sameersemna-hybrid-vision-mcp-cyyptl)