vision
Analyzes local image files (PNG, JPG, WebP, GIF, HEIC, SVG) via the Google Gemini API, providing vision capabilities such as describing UI elements or answering questions about images.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@visionanalyze /Users/jdoe/Pictures/photo.jpg"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
opencode-simple-vision-mcp — Vision MCP Server for Opencode
Cross-platform MCP server (macOS & Windows) for OpenCode that adds vision capabilities — analyze local PNG, JPG, WebP, GIF, HEIC and SVG files via the Google Gemini API.
Prerequisites
Node.js ≥ 18
Google Gemini API key (aistudio.google.com)
OpenCode running in the terminal
Related MCP server: MCP Vision Server
Setup
cd ~/opencode-simple-vision-mcp
npm install
cp .env.example .envEdit .env and add your API key:
GEMINI_API_KEY=your_api_key_here
GEMINI_MODEL=gemini-3.5-flashHandshake test
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"0.0.1"}}}' \
| node ~/opencode-simple-vision-mcp/server.mjs 2>/dev/nullExpected output: a JSON object with result.serverInfo.name: "vision".
OpenCode configuration
Find your Node.js path:
# macOS / Linux
which node
# e.g. /opt/homebrew/bin/node
# Windows (PowerShell)
where node
# e.g. C:\Program Files\nodejs\node.exeAdd to ~/.config/opencode/opencode.json:
{
"mcp": {
"vision": {
"type": "local",
"command": ["/opt/homebrew/bin/node", "/Users/YOURUSER/opencode-simple-vision-mcp/server.mjs"],
"enabled": true
}
}
}All variables are loaded from .env in the project directory.
Replace /Users/YOURUSER/ with your actual username. Use the full Node.js path from which node / where node (OpenCode does not inherit the shell PATH).
Do NOT use
~in thecommandarray. Node does not expand tilde —~/mcp-server/...will be treated as a literal path and the server will fail to start withCannot find module. Always use the full absolute path (e.g./Users/YOURUSER/mcp-server/...on macOS,C:\Users\YOURUSER\mcp-server\...on Windows).
nvm users: The Node path is version-specific (e.g.
/Users/YOURUSER/.nvm/versions/node/v24.14.1/bin/node). When you update Node vianvm install, this path changes and you must update the config. To avoid this, symlink a stable path (e.g.ln -s "$(which node)" ~/.local/bin/node) and use~/.local/bin/node(or/usr/local/bin/nodeif writable) in the config.
Usage
# macOS / Linux
analyze_image /Users/YOURUSER/Desktop/screenshot.png
analyze_image /path/to/image.jpg "What UI elements can you see?"
# Windows
analyze_image C:\Users\YOURUSER\Desktop\screenshot.png
analyze_image C:\path\to\image.jpg "What UI elements can you see?"Supported formats
Format | MIME type | Notes |
PNG |
| Native |
JPEG/JPG |
| Native |
WebP |
| Native |
GIF |
| Native |
HEIC/HEIF |
| Native |
SVG |
| Converted to PNG via sharp |
Troubleshooting
Status failed in OpenCode: Run the handshake test. If you get a JSON response, the issue is the Node.js path in your config. The most common cause is using ~ in the command array — Node does not expand tilde, so ["node", "~/mcp-server/.../server.mjs"] fails with Cannot find module. Use absolute paths for both the Node binary and the script.
GEMINI_API_KEY not found: Make sure .env exists in the project directory and contains the key (no quotes around the value).
404 from Gemini API: The configured model may be deprecated — set GEMINI_MODEL to gemini-3.5-flash in .env.
File not found: Always use absolute paths (no ~/ tilde notation). The script resolves ~/Desktop automatically for generated images.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables image analysis and understanding using Vision Language Models through OpenAI-compatible APIs. Supports analyzing images from URLs or local files with custom prompts.13MIT
- AlicenseAqualityCmaintenanceEnables Claude Code to describe images and extract text using Kimi/Moonshot vision API. Supports local image files with customizable prompts.2MIT
- AlicenseAqualityCmaintenanceEnables image analysis using any OpenAI-compatible vision API, supporting URLs, local files, or base64 input with custom prompts.1MIT
- AlicenseAqualityAmaintenanceEnables text-only coding agents to analyze local images using a dedicated vision provider, returning markdown and structured JSON evidence for screenshots, diagrams, UI mockups, and error captures.1137210MIT
Related MCP Connectors
Analyze images from multiple angles to extract detailed insights or quick summaries. Describe visu…
OCR, transcription, file extraction, and image generation for AI agents via MCP.
LLM chat, text summarization and AI image generation
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/larsburkhardt/opencode-simple-vision-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server