loading…
Search for a command to run...
loading…
An MCP server that analyzes images using OpenRouter's Gemini Flash model, supporting local file paths and URLs.
An MCP server that analyzes images using OpenRouter's Gemini Flash model, supporting local file paths and URLs.
OpenRouter-powered image analysis MCP. GLM 5.1 image বুঝে না, তাই এই MCP Gemini Flash দিয়ে image analyze করে।
cd vision-mcp
npm install
Trae AI → Settings → MCP Servers → Edit config JSON।
নিচের block টা mcpServers এর ভেতরে add করো:
"vision-mcp": {
"command": "node",
"args": ["C:/Users/TOMAR_NAME/vision-mcp/index.js"],
"env": {
"OPENROUTER_API_KEY": "sk-or-v1-YOUR_KEY_HERE",
"VISION_MODEL": "google/gemini-2.0-flash-exp:free"
}
}
⚠️ args এ full path দিতে হবে। Windows হলে backslash \\ অথবা forward slash / দুটোই চলে।
OPENROUTER_API_KEY এর জায়গায় তোমার key বসাও।
Key পাবে: https://openrouter.ai/keys
Trae-এ যেকোনো chat-এ বলো:
analyze this image: C:/Users/akash/Desktop/screenshot.png
অথবা URL দিয়ে:
analyze this image url: https://example.com/photo.jpg
VISION_MODEL পরিবর্তন করে যেকোনোটা use করতে পারো:
| Model | Quality |
|---|---|
google/gemini-2.0-flash-exp:free |
✅ Best (default) |
meta-llama/llama-4-scout:free |
✅ Good |
meta-llama/llama-4-maverick:free |
✅ Good |
Run in your terminal:
claude mcp add vision-mcp -- npx Yes, Vision MCP is free — one-click install via Unyly at no cost.
No, Vision runs without API keys or environment variables.
Self-hosted: the server runs locally on your machine via the install command above.
Open Vision on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
CSA PROJECT - FZCO © 2026 IFZA Business Park, DDP, Premises Number 31174 - 001
Security
Low riskAutomated heuristic from public metadata — not a security guarantee.