Ui.Vision MCP — Claude Code MCP server: what it does, how to install
Connect an AI agent to Ui.Vision for browser and desktop automation. Use it to run macros, inspect screenshots, or interact with on-screen controls through OCR.
claude mcp add --env UIVISION_MCP_PORT=<UIVISION_MCP_PORT> --transport stdio mcp -- npx -y uivision-mcp-bridgeWhat Ui.Vision MCP does
The agent can create and run macros with the uiv.* API, then inspect logs and screenshots. Web pages can be controlled through the DOM or Chrome input; desktop apps and other screen content are handled visually with OCR and image search.
The uivision-mcp-bridge package relays requests to the Ui.Vision extension. Tools run in the side panel, so it needs to stay open; otherwise calls return a connection error. The server supports Claude Code, Codex, Cursor, GitHub Copilot, Windsurf, Cline, and Zed.
What it helps with
- control web pages through the DOM or Chrome input
- locate screen controls with OCR and image search
- run a macro and inspect its log
- interact with desktop apps using mouse and keyboard input
Example prompts for the agent
- Use Ui.Vision OCR to find the button on screen and click it.
- Run the
checkoutmacro and inspect its execution log. - Take a screenshot and describe what is open in the browser.
How to install Ui.Vision MCP
Platform CLI
claude mcp add --env UIVISION_MCP_PORT=<UIVISION_MCP_PORT> --transport stdio mcp -- npx -y uivision-mcp-bridgeReplace <…> with your own values
Platform CLI
codex mcp add mcp --env UIVISION_MCP_PORT=<UIVISION_MCP_PORT> -- npx -y uivision-mcp-bridgeReplace <…> with your own values
Config file
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"uivision-mcp-bridge"
],
"env": {
"UIVISION_MCP_PORT": "<UIVISION_MCP_PORT>"
}
}
}
}Replace <…> with your own values
Config file
{
"servers": {
"mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"uivision-mcp-bridge"
],
"env": {
"UIVISION_MCP_PORT": "<UIVISION_MCP_PORT>"
}
}
}
}Replace <…> with your own values
Platform CLI
gemini mcp add -e UIVISION_MCP_PORT=<UIVISION_MCP_PORT> mcp npx -y uivision-mcp-bridgeReplace <…> with your own values
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Ui.Vision MCP
How do I install Ui.Vision MCP in Claude Code?
Run claude mcp add uivision-mcp -- npx -y uivision-mcp-bridge, then quit and reopen Claude Code. In the Ui.Vision side panel, enable the bridge under Settings → AI.
What does Ui.Vision MCP do?
It connects an agent to the Ui.Vision extension for browser and desktop automation. The agent can run macros, inspect screenshots, and control on-screen interfaces.
Does the Ui.Vision side panel need to stay open?
Yes. Tools run in the panel context; calls return “extension not connected” when it is closed.
