Visual Desktop Bridge - Give any AI full control over Windows to automate apps and inputs.
Bridge MCP MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Visual Desktop Bridge - Give any AI full control over Windows to automate apps and inputs.
Bridge MCP v2.0 stores agent registrations in a persistent JSON file:
Once Bridge MCP is connected, these are the calls the assistant has available:
desktop — //screenshot/latest - Current screenshotfile — ///{path} - Read any desktop fileautomate_desktop_task — Step-by-step task automationdebug_error — Interactive error debuggingweb_automation — Playwright web workflowsapp_launch — Launch an applicationapp_switch — Switch to open appapp_close — Close an applicationapp_list — List all open appsclick — Click at coordinatesdouble_click — Double-clickright_click — Right-clickInstallation goes through your MCP client rather than a global install: point it at fastmcp on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
This sits in the browser automation group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Bridge MCP's toolset — desktop, file, automate_desktop_task and 11 more — is a fair guide to whether it matches your workflow. It is maintained by BarhamAgha1; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Bridge MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| desktop | //screenshot/latest - Current screenshot |
| file | ///{path} - Read any desktop file |
| automate_desktop_task | Step-by-step task automation |
| debug_error | Interactive error debugging |
| web_automation | Playwright web workflows |
| app_launch | Launch an application |
| app_switch | Switch to open app |
| app_close | Close an application |
| app_list | List all open apps |
| click | Click at coordinates |
| double_click | Double-click |
| right_click | Right-click |
| type_text | Type text |
| press_key | Press a key |
{
"mcpServers": {
"bridge": {
"command": "uvx",
"args": ["fastmcp"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.