Global AI chat room · 17 online now Join now
T
MCP SERVER Listed

tan-yong-sheng/ai-vision-mcp

The ai-vision-mcp server bridges the gap between LLMs and visual data by integrating Google Gemini and Vertex AI directly into the Model Context Protocol. Unlike basic image-to-text tools, this server provides structured visual analysis, making it particularly useful for developers handling UI/UX audits or automated visual regression testing. It allows an AI agent to 'see' and interpret interfaces across different operating systems, enabling tasks like identifying layout shifts, verifying element placement, or analyzing video frames for behavioral bugs. By exposing these multimodal capabilities as MCP tools, it removes the need to manually upload screenshots to a chat interface, allowing the AI to trigger visual inspections programmatically during the development workflow.

Open ecosystemSearch
View GitHub
01 / SERVER DETAIL

Server detail

The ai-vision-mcp server bridges the gap between LLMs and visual data by integrating Google Gemini and Vertex AI directly into the Model Context Protocol. Unlike basic image-to-text tools, this server provides structured visual analysis, making it particularly useful for developers handling UI/UX audits or automated visual regression testing. It allows an AI agent to 'see' and interpret interfaces across different operating systems, enabling tasks like identifying layout shifts, verifying element placement, or analyzing video frames for behavioral bugs. By exposing these multimodal capabilities as MCP tools, it removes the need to manually upload screenshots to a chat interface, allowing the AI to trigger visual inspections programmatically during the development workflow.

An MCP server that exposes tan-yong-sheng/ai-vision-mcp capabilities to MCP-compatible AI clients.

CapabilitiesSearchMCPOpen source
ProtocolModel Context Protocol
Developer ecosystemOpen ecosystem
LicenseMIT / check source
SourceGitHub
COLLECTIONS

Collections featuring this MCP

Popular MCP2026.03.30Listed
My MCP2026.03.31Listed
Genie2026.03.30Listed
02 / TOOL TESTING

Tool testing

AVAILABLE TOOL

tan-yong-sheng-ai-vision-mcp

Callable

Call the MCP capabilities provided by tan-yong-sheng/ai-vision-mcp and return a structured result.

PARAMETERS
inputPass arguments according to the server tool schema.
Tip: the tool may truncate responses. Use pagination parameters such as start_index to read long content in chunks.
03 / SERVICE CONFIGURATION

Connection modes

Remote
{
  "mcpServers": {
    "tan-yong-sheng/ai-vision-mcp": {
      "url": "Generated by the provider after deployment"
    }
  }
}

The Remote endpoint is generated by the provider after deployment; this page does not fabricate an unusable endpoint.

03 / WORKFLOW

How to use

  1. 01
    Step 1

    Review server capabilities and permission scope.

  2. 02
    Step 2

    Copy the install command or JSON configuration.

  3. 03
    Step 3

    Run a small connection test in your client.

  4. 04
    Step 4

    Adopt it long term only after reviewing access and maintenance.

04 / DISCUSSIONS

Discussions

Use this space to keep checking source information, usage experience and maintenance status.

Open source page
Email