vision-mcp
An MCP server that analyzes images using OpenRouter's Gemini Flash model, supporting local file paths and URLs.
Ask AI about vision-mcp
Powered by Claude · Grounded in docs
I know everything about vision-mcp. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
Vision MCP for Trae AI
OpenRouter-powered image analysis MCP. GLM 5.1 image বুঝে না, তাই এই MCP Gemini Flash দিয়ে image analyze করে।
Setup (3 step)
Step 1 — Install
cd vision-mcp
npm install
Step 2 — Trae MCP Config
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।
Step 3 — API Key
OPENROUTER_API_KEY এর জায়গায় তোমার key বসাও।
Key পাবে: https://openrouter.ai/keys
Use করো
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 Models (Free)
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 |
