Chrome Bridge
Related Servers
Alternatives to Chrome Bridge
No user-submitted related servers found.
Related Servers
- AlicenseBqualityCmaintenanceTurns Chrome into a local MCP server, giving AI agents 51 browser tools to inspect DOM, automate clicks, run JavaScript, audit security and accessibility, mock APIs, extract data, record demos, and more from any MCP client.92671 npmMIT
- AlicenseNot gradedqualityBmaintenanceMCP server that lets agents drive your real Chrome browser with existing logins and sessions via an outbound-only WebSocket extension. It exposes Playwright-compatible browser tools for navigation, clicking, typing, and snapshots.1Apache 2.0
- AlicenseNot gradedqualityAmaintenanceA native MCP server that gives AI assistants full Chrome control via the DevTools Protocol and an unpacked extension, including semantic element refs, real input, screenshots, and browser/tab/window management. It exposes 43 callable tools with a visible control overlay and an optional read-only security profile.2MIT
- AlicenseNot gradedqualityAmaintenancesingle-binary MCP server that gives AI agents a browser. 66 tools for navigation, form filling, data extraction, screenshots, and DOM diffing — built on pure Chrome DevTools Protocol.13MIT
- AlicenseAqualityAmaintenanceMCP server that drives your real Chrome/Edge/Opera browser through a Chrome extension and DevTools Protocol, preserving logins and session state, and can also perform OS-level mouse and keyboard input behind approval.5146 PyPI1MIT

T3rnel Browser — Sessionofficial
AlicenseAqualityBmaintenanceDrives the browser you are already signed into, so work behind a login, SSO or MFA needs no scripted auth. A local stdio MCP server talking to the free T3rnel Browser extension over a native-messaging relay. 20 tools standalone; 99 with the extension — CSS-as-component export, full-page capture, React inspector, network and console capture, form filling, record and replay. Nothing hosted.2256 npm2Apache 2.0
TDQS
Scored across 59 tools
Most tools have clear, distinct purposes. Overlap exists among reading tools (read_page, extract, extract_table, find_text, query_dom) but each targets a different structure or use case, so ambiguity is limited. A few similar-sounding pairs (watch vs watch_dom, screenshot vs element_screenshot) are still distinct enough.
The naming convention is mostly verb_noun (e.g., navigate, get_page_info, type_text, extract_table), but there are many variations: bare verbs (click, scroll, hover, watch), noun-style names (cookie_audit, session_fixture, handoff), and mixed prefixes (get_, set_, find_, read_, create_, manage_). This inconsistency makes the API slightly less predictable.
With 59 tools, the count is well above the typical MCP range (3–15) and feels heavy for a single server. While the breadth covers many browser automation features, several tools could be consolidated (e.g., get_page_info/query_dom/read_page), suggesting the set is larger than necessary.
The surface is exceptionally comprehensive, covering navigation, DOM interaction, forms, screenshots, file handling, dialogs, storage, cookies, performance/accessibility audits, session recording, network interception, and even human handoff. No significant gaps for a browser automation use case.