This MCP server analyzes images and YouTube videos using the Gemini API without requiring local downloads.
From the registry: Analyze images and videos with Gemini to get fast, reliable visual insights. Handle content from U…
$ git clone https://github.com/Artin0123/gemini-vision-mcp.git && cd gemini-vision-mcp && npm install && npm run buildPlease install the `artin0123-gemini-image-mcp-server` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Gemini API key** — Create a Gemini API key in Google AI Studio (https://aistudio.google.com/app/apikey)
- **Clone and build** — Clone repo, install deps, and build Run: `git clone https://github.com/Artin0123/gemini-vision-mcp.git && cd gemini-vision-mcp && npm install && npm run build`
Canonical MCP server config (stdio transport):
- command: `node`
- args: ["<absolute-path-to-repo>/dist/index.js"]
- required environment variables:
- `GEMINI_API_KEY`: Your Gemini API key (example: `<your_api_key>`)
- optional environment variables:
- `GEMINI_MODEL`: Override the Gemini model (example: `models/gemini-flash-lite-latest`)
Note: Analyzes image URLs (<=16MB) and YouTube videos via Gemini. Smithery install also supported.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.GEMINI_API_KEYrequiredAPI key for accessing the Gemini API.GEMINI_MODELOptional environment variable to override the default Gemini model.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.