OpenChrome
Related Servers
Alternatives to OpenChrome
No user-submitted related servers found.
Related Servers
- AlicenseBqualityDmaintenanceEnables AI agents to fully control Google Chrome: navigate, click, fill forms, inspect DevTools, and manage tabs with parallel execution and session isolation.2415MIT
- AlicenseBqualityFmaintenanceEnables AI agents to directly control your real Chrome browser with full context including login sessions, cookies, and open tabs. It provides tools for page scanning, JavaScript execution, CDP control, screenshots, and physical mouse/keyboard input for authentic browser automation.20243MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants and terminal users to control a logged-in Chrome browser, performing actions like opening pages, searching, filling forms, and taking screenshots without re-authentication.1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to fully control a browser for web automation, including navigation, clicking, typing, scrolling, screenshots, and DOM inspection, with session persistence and anti-bot bypass.14MIT
- AlicenseNot gradedqualityCmaintenanceLets AI assistants control your real Chrome browser to perform web tasks like reading pages, taking screenshots, clicking, and typing, using your existing logged-in sessions.131MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to securely control a user's existing signed-in Chrome browser through isolated tab groups, with strict per-session ownership and no cookie or token exposure.3ISC
TDQS
Scored across 121 tools
Massive functional overlap across the surface: act/interact/computer all perform element actions; read_page/page_content both retrieve page content; oc_task_*, oc_run_*, and oc_task_run_* form three interleaved tracking families that are genuinely hard to tell apart; oc_observe/query_dom/find/inspect all do element discovery. An agent would frequently pick the wrong tool despite reading descriptions.
Two parallel naming families coexist: namespaced oc_* tools (oc_browser_control, oc_evidence_get) alongside unnamespaced legacy tools (tabs_activate, read_page, interact, act). Verbs are inconsistent (tabs_create vs oc_task_start; list_profiles vs oc_profile_status), and several names are semantically opaque without the description (oc_diff, oc_query, oc_reflect, oc_journal).
The header claims 121 tools and ~64 are actually described — far beyond any reasonable browser-automation surface. The TaskRun/Run/task/run families alone account for ~15 near-duplicate tools, and niche utilities like oc_totp_generate, oc_doctor_report, oc_reap_orphans, and oc_normalize_action inflate the count well past what an agent can reliably navigate.
The browser-automation domain is exhaustively covered: navigation, tabs, DOM querying, element interaction, form filling, screenshots, cookies, devtools URLs, console/network capture, evidence bundling, session recording, profiling, and task lifecycle tracking. There are essentially no gaps in the coverage — if anything the surface overshoots complete.