# image-recognition-mcp

Connects AI assistants to OpenAI vision models for analyzing remote graphics. Useful when your coding agent needs to inspect a picture via a link.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 5
- Author: mcp-s-ai
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/mcp-s-ai/image-recognition-mcp
- Updated: 2025-09-10
- HTML: https://affpapa.org/en/nevibecode/mcp/image-recognition-mcp

## What it 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.

## Requirements
- Needs: Node.js (commands run via npx)
- Environment variables: `OPENAI_API_KEY` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add image-recognition-mcp -e OPENAI_API_KEY=<OPENAI_API_KEY> -- npx -y image-recognition-mcp
```
Replace <…> with your own values

### Codex

**Platform CLI**
```bash
codex mcp add image-recognition-mcp --env OPENAI_API_KEY=<OPENAI_API_KEY> -- npx -y image-recognition-mcp
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "image-recognition-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "image-recognition-mcp"
            ],
            "env": {
                "OPENAI_API_KEY": "<OPENAI_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "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

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e OPENAI_API_KEY=<OPENAI_API_KEY> image-recognition-mcp npx -y image-recognition-mcp
```
Replace <…> with your own values

## When to use it
- inspect remote pictures using OpenAI vision models
- retrieve textual scene summaries through the `describe-image` tool
- feed graphic references from external links directly into agent workflows

## Example prompts
- Explain the scene shown in this picture: <imageUrl>
- Run `describe-image` for the asset at <imageUrl>
- Inspect the screenshot at <imageUrl> and summarize its contents

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 107701
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26673
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23283
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9369
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9298

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md