Multi-backend AI vision for MCP agents. Analyze images, screenshots, and documents using local Ollama models or cloud APIs like OpenAI, Google Gemini, and OpenRouter.
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.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
process.env. You'll be asked to provide them before it can run.GOOGLE_API_KEY— [Free Tier APIs](#-backends) Zero-cost cloud vision via Google/OpenRouter Set or OPENROUTER_API_KEYMAX_TOKENS— 2048 Max response tokensOCR_MODEL— minicpm-v:latest Default OCR modelOLLAMA_HOST— "": "127.0.0.1:11434",OLLAMA_PORT— 11434 Ollama API portOPENAI_API_KEY— [Paid APIs](#-backends) OpenAI GPT-4o, Claude Vision, any OpenAI-compatible SetOPENROUTER_API_KEY— [Free Tier APIs](#-backends) Zero-cost cloud vision via Google/OpenRouter Set GOOGLE_API_KEY orVISION_KEEP_ALIVE— 10m Model keep-alive durationVISION_MAX_RETRIES— 3 Retry attempts on failureVISION_MODEL— "": "minicpm-v:latest"VISION_TIMEOUT_MS— 120000 Request timeout (ms)VISION_WARMUP_ON_START— 1 Auto-warmup model on server start[](https://m8ven.ai/mcp/mr-joe1-opensight-mcp-jr7vow)