image-recognition-mcp — Claude Code MCP server: what it does
Connects AI assistants to OpenAI vision models for analyzing remote graphics. Useful when your coding agent needs to inspect a picture via a link.
claude mcp add image-recognition-mcp -e OPENAI_API_KEY=<OPENAI_API_KEY> -- npx -y image-recognition-mcpWhat image-recognition-mcp does
The server exposes the describe-image tool, taking an imageUrl parameter to inspect external graphics. It sends the target address to OpenAI vision models and delivers a textual explanation back to the assistant.
Written in TypeScript, the package runs through npx and depends on Node.js 18 or newer. The code includes validation routines for network dropouts and bad URLs.
Without a valid OPENAI_API_KEY containing available account credits, the server fails immediately upon start.
What it helps with
- inspect remote pictures using OpenAI vision models
- retrieve textual scene summaries through the
describe-imagetool - feed graphic references from external links directly into agent workflows
Example prompts for the agent
- Explain the scene shown in this picture: <imageUrl>
- Run
describe-imagefor the asset at <imageUrl> - Inspect the screenshot at <imageUrl> and summarize its contents
How to install image-recognition-mcp
Platform CLI
claude mcp add image-recognition-mcp -e OPENAI_API_KEY=<OPENAI_API_KEY> -- npx -y image-recognition-mcpReplace <…> with your own values
Platform CLI
codex mcp add image-recognition-mcp --env OPENAI_API_KEY=<OPENAI_API_KEY> -- npx -y image-recognition-mcpReplace <…> with your own values
Config file
{
"mcpServers": {
"image-recognition-mcp": {
"command": "npx",
"args": [
"-y",
"image-recognition-mcp"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>"
}
}
}
}Replace <…> with your own values
Config file
{
"servers": {
"image-recognition-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"image-recognition-mcp"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>"
}
}
}
}Replace <…> with your own values
Platform CLI
gemini mcp add -e OPENAI_API_KEY=<OPENAI_API_KEY> image-recognition-mcp npx -y image-recognition-mcpReplace <…> with your own values
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about image-recognition-mcp
How to install image-recognition-mcp in Claude Code?
Run claude mcp add image-recognition-mcp -e OPENAI_API_KEY=<OPENAI_API_KEY> -- npx -y image-recognition-mcp. Replace <OPENAI_API_KEY> with your active OpenAI secret key.
What does image-recognition-mcp do?
It gives your AI client access to the describe-image tool, letting vision models inspect graphics hosted at any provided URL.
What dependencies does image-recognition-mcp require?
You need Node.js 18 or above, npm or yarn, plus an OPENAI_API_KEY environment variable with positive account credits.
