BrowserDo
Related Servers
Alternatives to BrowserDo
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceMCP server that lets AI agents drive the locally installed Chrome or Edge, opening pages, taking compact accessibility-tree snapshots with @e references, and clicking, typing, scrolling, or capturing screenshots. It also exposes multi-account and cross-channel tab switching, tab sync rules, and ad-block/perf statistics.MIT
- AlicenseAqualityAmaintenanceMCP server for AgentGo, a real Chromium browser for AI agents: compact page outlines with stable refs, diff-only replies after each action, real mouse and keyboard input, the agent's own signed-in accounts, and human approval for payments. MIT.111MIT
- AlicenseNot gradedqualityBmaintenanceA local Streamable HTTP MCP server that lets several AI agents drive your real, logged-in Chrome at once, each isolated in its own background tab group without stealing focus. It exposes browser tools for navigating, reading pages, filling forms, signing in via Bitwarden, and handing steps back to the user.MIT
- AlicenseAqualityAmaintenanceMCP server that lets AI agents drive your real Chromium browser with your existing signed-in sessions, providing visible, local, and inspectable automation for tasks like navigation, clicking, typing, and form filling.251Apache 2.0
- AlicenseNot gradedqualityAmaintenanceLocal browser MCP server that lets AI assistants control a real desktop browser via tools like navigate, snapshot, and search_web.MIT
- AlicenseNot gradedqualityAmaintenanceA local MCP server that lets AI coding assistants drive the user's own already-signed-in Chrome, so agents can read logged-in pages, click, fill forms, navigate, screenshot, inspect network traffic and storage, and run multi-step browser workflows without a separate headless browser or remote debugging port. All communication stays on the user's machine and agent-opened tabs are grouped so they never steal focus.1 npmISC
TDQS
Scored across 31 tools
Most tools have clearly distinct purposes and the descriptions explicitly disambiguate tricky pairs such as browser_stop_task vs browser_stop_loading and browser_navigate vs browser_new_tab. A few boundaries remain potentially confusable, especially browser_run_task vs the manual snapshot/click/input workflow, and browser_read_pages vs navigating a tab and snapshotting it.
Every tool uses the same browser_ prefix followed by a snake_case verb or verb_noun phrase. The pattern is predictable throughout, making the set easy to scan and remember.
31 tools is very large for the stated scope, even for browser automation. Several granular operations such as go_back/go_forward/reload, new/close tab/window, and show/minimize/mute could plausibly be consolidated or exposed through fewer parameterized tools.
The surface covers an unusually full browser lifecycle: navigation, tab/window management, snapshots, clicking, typing, keyboard, scrolling, dragging, waiting, popups, batch actions, and human handover. Minor gaps remain around file upload/download and visual screenshot capture, but core automation workflows are well covered.