Home / MCP servers / Other / ai-vision-mcp

ai-vision-mcp

ai-vision-mcp is a MCP server by tan-yong-sheng that image, video and object-detection analysis with Google Gemini and Vertex AI for UI/UX evaluation, visual regression testing and interface understanding.

Updated 2026-04-06

What is ai-vision-mcp?

ai-vision-mcp is a MCP server by tan-yong-sheng that image, video and object-detection analysis with Google Gemini and Vertex AI for UI/UX evaluation, visual regression testing and interface understanding. It is listed under Other and has 80 GitHub stars.

TypeMcp server
Authortan-yong-sheng
Repositorytan-yong-sheng/ai-vision-mcp
Popularity80 GitHub stars
CategoryOther
SecurityLow risk (96/100)
Rank#673 of 4,418 MCP servers; #101 in Other
LicenseMIT
Last commit2026-04-06
RunsLocally
LanguageTypeScript
PlatformsmacOS, Windows, Linux

Is ai-vision-mcp safe to install?

ai-vision-mcp scores 96/100 on the MCPMods security check: Low risk. No checks raised a concern. It passed 5 of 6 checks.

MCP server results come from listing signals: who publishes it, where your data goes and what it can do. The code itself is not scanned yet.

CheckResult
Community-built serverNote
Runs on your machine onlyPass
No credentials mentionedPass
Read-only by descriptionPass
No code executionPass
Source on GitHubPass

How do I install ai-vision-mcp?

  1. Find the launch command. The README says how the server starts (npx, uvx, docker or a remote URL) and which API keys it needs.
    https://github.com/tan-yong-sheng/ai-vision-mcp
  2. Add it to Claude Code. Replace the part after -- with the command from the README. Remote servers use --transport http with a URL.
    claude mcp add ai-vision-mcp -- <command from README>
    claude mcp add --transport http ai-vision-mcp <server-url>
  3. Check it connected. This lists your MCP servers and their status.
    claude mcp list

Or ask Claude to set it up

Paste this into Claude Code and it installs ai-vision-mcp for you:

Add the "ai-vision-mcp" MCP server from https://github.com/tan-yong-sheng/ai-vision-mcp to Claude Code. Read its README for the launch command and any API keys I need, run claude mcp add, then check that it connects.