MCP Image Recognition Server

An MCP server that provides image recognition 👀 capabilities using Anthropic and OpenAI vision APIs

Catalog onlyCatalog onlySTDIO

Overview

MCP Image Recognition Server is an MCP server that provides image recognition capabilities using Anthropic and OpenAI vision APIs.

To use the server, clone the repository, configure your environment file with API keys, and run the server in development mode or directly.

Image description using Anthropic Claude Vision or OpenAI GPT-4 Vision - Support for multiple image formats (JPEG, PNG, GIF, WebP) - Configurable primary and fallback providers - Base64 and file-based image input support - Optional text extraction using Tesseract OCR

Describing images for accessibility purposes.
Analyzing images for content moderation.
Extracting text from images for data entry automation.

Add to your AI client

Use these steps to connect MCP Image Recognition Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-image-recognition-mario-andreschak": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-image-recognition-mario-andreschak"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "mcp-image-recognition-mario-andreschak": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-image-recognition-mario-andreschak"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "mcp-image-recognition-mario-andreschak": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-image-recognition-mario-andreschak"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "mcp-image-recognition-mario-andreschak": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-image-recognition-mario-andreschak"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-image-recognition-mario-andreschak": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-image-recognition-mario-andreschak"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mcp-image-recognition-mario-andreschak": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-image-recognition-mario-andreschak"
      ]
    }
  }
}

FAQ

What image formats are supported?

The server supports JPEG, PNG, GIF, and WebP formats.

Is Tesseract OCR required?

Tesseract OCR is optional and only needed if you want to enable text extraction from images.

How do I configure the server?

You need to set your API keys and preferences in the .env file after cloning the repository.

Research and data