Snowfort Circuit MCP - Computer use for webapps and electron apps
Snowfort Circuit MCP - Computer use for webapps and electron apps
Circuit MCP is a comprehensive Model Context Protocol (MCP) server suite that enables AI coding agents to automate both web browsers and Electron desktop applications with unparalleled precision and flexibility.
Once Circuit MCP is connected, these are the calls the assistant has available:
Cross — Browser Support**: Chromium, Firefox, WebKitNavigation — History control, page reload, URL navigationMulti — Window Management**: Control multiple app windows simultaneouslyAccessibility-First — Built-in accessibility tree navigation with element refsbrowser_launch — Launch browser with AI optimizationsbrowser_navigate — Navigate to URL (includes auto-snapshot)browser_resize — Resize browser viewportbrowser_handle_dialog — Set dialog auto-responsebrowser_tab_new — Create new browser tabbrowser_tab_list — List all open tabsbrowser_tab_select — Switch to specific tabbrowser_tab_close — Close specific tabbrowser_launch — Launch browser with AI optimizationsbrowser_navigate — Navigate to URL (includes auto-snapshot)browser_resize — Resize browser viewportbrowser_handle_dialog — Set dialog auto-responsebrowser_tab_new — Create new browser tabbrowser_tab_list — List all open tabsbrowser_tab_select — Switch to specific tabbrowser_tab_close — Close specific tabbrowser_network_requests — Get network request historybrowser_console_messages — Get console message historyCompare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| browser_launch | Launch browser with AI optimizations |
| browser_navigate | Navigate to URL (includes auto-snapshot) |
| browser_resize | Resize browser viewport |
| browser_handle_dialog | Set dialog auto-response |
| browser_tab_new | Create new browser tab |
| browser_tab_list | List all open tabs |
| browser_tab_select | Switch to specific tab |
| browser_tab_close | Close specific tab |
| browser_network_requests | Get network requests from Electron app |
| browser_console_messages | Get console logs from Electron app |
| browser_generate_playwright_test | Generate test code from actions |
| click | Click element (includes auto-snapshot) |
| hover | Hover over element (includes auto-snapshot) |
| drag | Drag element to target |
| key | Press keyboard key (includes auto-snapshot) |
| select | Select dropdown option |
| upload | Upload file to input |
| back | Navigate back in history |
| forward | Navigate forward in history |
| refresh | Reload current page |
| screenshot | Take compressed screenshot |
| snapshot | Get accessibility tree with element refs |
| Generate PDF of page | |
| content | Get HTML content |
| text_content | Get visible text |
| evaluate | Execute JavaScript |
| wait_for_selector | Wait for element |
| close | Close browser session |
| app_launch | Launch Electron app with AI optimizations |
| get_windows | List windows with type identification |
| ipc_invoke | Call IPC method |
| fs_write_file | Write file to disk |
| fs_read_file | Read file from disk |
| keyboard_press | Press key with modifiers |
| click_by_text | Click element by text |
| click_by_role | Click by accessibility role |
| click_nth | Click nth matching element |
| keyboard_type | Type with delay |
| add_locator_handler | Handle modals/popups |
| wait_for_load_state | Wait for page state |
| smart_click | Smart click with auto-detection (refs/text/CSS) |
{
"mcpServers": {
"circuit-web": {
"command": "npx",
"args": [
"@snowfort/circuit-web@latest"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Use Microsoft’s Playwright MCP server to navigate pages, inspect accessibility snapshots, fill forms and capture browser screenshots.
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.
Enables AI-powered applications to monitor and interact with browser data via a Chrome extension and MCP.
Automates browsers and APIs, enabling Large Language Models (LLMs) to interact with web pages for tasks like screenshot capture and JavaScript