MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add ui-vision -- npx -y uivision-mcp-bridge~/.codex/config.toml
[mcp_servers.ui-vision]
command = "npx"
args = ["-y", "uivision-mcp-bridge"]
# codex mcp add ui-vision -- npx -y uivision-mcp-bridge~/.cursor/mcp.json
{
"mcpServers": {
"ui-vision": {
"command": "npx",
"args": [
"-y",
"uivision-mcp-bridge"
]
}
}
}.vscode/mcp.json
{
"servers": {
"ui-vision": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"uivision-mcp-bridge"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"ui-vision": {
"command": "npx",
"args": [
"-y",
"uivision-mcp-bridge"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"ui-vision": {
"command": "npx",
"args": [
"-y",
"uivision-mcp-bridge"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"ui-vision": {
"command": "npx",
"args": [
"-y",
"uivision-mcp-bridge"
]
}
}
}