Artin0123-gemini-image-mcp-server
UnexploredAnalyze images and videos with Gemini to get fast, reliable visual insights. Handle content from U…
Install
mcp_config.json
{
"mcpServers": {
"ai-smithery-artin0123-gemini-image-mcp-server": {
"url": "https://server.smithery.ai/@Artin0123/gemini-image-mcp-server/mcp",
"type": "streamable-http"
}
}
}Documentation
image-mcp-server-gemini
This is remote server, use local version for local images and videos.
Features
- Analyze one or more image URLs with a single tool call.
- Analyze YouTube videos without downloading files locally.
- Supply an API key and optionally override the Gemini model via environment variables.
- File size limit: Images are limited to 16 MB to ensure fast processing.
- YouTube videos: No size limit as they are streamed directly by Gemini API.
Installation
Installing via Smithery
Install the server in Claude Desktop:
npx -y @smithery/cli install @Artin0123/gemini-image-mcp-server --client claude
Manual Installation
# Clone the repository
git clone https://github.com/Artin0123/gemini-vision-mcp.git
cd gemini-vision-mcp
# Install dependencies
npm install
# Compile TypeScript to dist/
npm run build
Configuration
Create a Gemini API key in Google AI Studio and provide GEMINI_API_KEY to the server.
{
"mcpServers": {
"gemini-media": {
"command": "node",
"args": ["/absolute/path/to/gemini-vision-mcp/dist/index.js"],
"env": {
"GEMINI_API_KEY": "your_api_key_here",
"GEMINI_MODEL": "models/gemini-flash-lite-latest"
}
}
}
}
If no key is supplied, the server can still start (handy for automated scans), but any tool invocation will return a configuration error until a valid API key is configured.
Model override
The server defaults to models/gemini-flash-lite-latest. Override it by either:
Setting the
GEMINI_MODELenvironment variable, or ProvidingmodelNamein the Smithery/SDK configuration schema.
Available tools
analyze_image: Analyze one or more image URLs. Maximum file size: 16 MB per image.analyze_youtube_video: Analyze a YouTube video from URL. No size limit.
Image URLs are downloaded and processed with a 16 MB size limit to ensure fast response times. Files exceeding this limit will result in an error message indicating the actual file size.
YouTube videos are streamed directly by Gemini API without downloading, so there is no size restriction.
Prompt examples
Please analyze this product photo: https://teimg-bgr.pages.dev/file/mvYT6KeF.webp
Extract the main talking points from this clip: https://www.youtube.com/watch?v=dQw4w9WgXcQ
Development
npm install
npm test
npm run build
The test suite exercises URL forwarding, MIME handling, and configuration fallbacks.
License
MIT
Sourced from the repository README.
More in AI & Agents
- PonytailMakes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.109,599
- AgentsMulti-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, and Google Antigravity39,079
- Frontend SlidesCreate beautiful slides on the web using a coding agent's frontend skills28,060
- Agent Skills Search ServerSearch and discover Agent Skills from the skills.sh registry. Powered by HAPI MCP server.24,658
- Agency Agents Zh🎭 267 个即插即用的 AI 专家角色 — 支持 Hermes Agent/Claude Code/Cursor/Copilot 等 18 种工具,覆盖工程/设计/营销/金融等 20 个部门。含 52 个中国市场原创智能体(小红书/抖音/微信/飞书/钉钉等)。搭配编排器 agency-orchestrator,一句话即可让多位专家按 DAG 自动协作。19,868
- Watermarks RemoverStrip multi-vendor AI provenance marks: Unicode text hygiene, statistical rewrite hooks, and C2PA/metadata from PNG/JPEG/SVG/PDF/DOCX/HTML/MD17,822