tan-yong-sheng/ai-vision-mcp

Overview

A Model Context Protocol (MCP) server that adds vision capabilities to analyze images and video. It is written in TypeScript and integrates with MCP-compatible clients to enable visual data processing within AI workflows.

Best for

Best for
Developers building MCP-based applications that need basic image and video analysis

Use cases

• Extract content from images via MCP-based agents
• Analyze video frames for object or scene detection
• Integrate vision analysis into existing MCP toolchains

How to use

Install

npx ai-vision-mcp

Tools exposed

• analyze_image
• compare_images

Tested with

Claude Desktop, Claude Code, Cursor, Cline

Example client config

{\n  "mcpServers": {\n    "ai-vision-mcp": {\n      "command": "npx",\n      "args": ["ai-vision-mcp"],\n      "env": {\n        "IMAGE_PROVIDER": "google",\n        "VIDEO_PROVIDER": "google",\n        "GEMINI_API_KEY": "your-gemini-api-key"\n      }\n    }\n  }\n}

Notes

A Model Context Protocol (MCP) server that adds vision capabilities to analyze images and video. It is written in TypeScript and integrates with MCP-compatible clients to enable visual data processing within AI workflows.

54 stars on GitHub. Last updated 2026-04-06. Licensed MIT.

Use cases

• Extract content from images via MCP-based agents
• Analyze video frames for object or scene detection
• Integrate vision analysis into existing MCP toolchains

Pros

• Open source and free to use
• Written in TypeScript for type safety and maintainability
• Provides vision functionality within the MCP ecosystem

Cons

• Limited community adoption (54 stars) may indicate fewer resources or slower updates
• Requires an MCP-compatible client or host to function
• Vision capabilities may be less comprehensive than dedicated vision APIs

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.