jevpilot
Related Servers
Alternatives to jevpilot
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to drive a real Chrome browser for autonomous web tasks, using fast typed decisions with calibrated confidence, human-in-the-loop questions, safety gates, and full debug traces.1,633 npm1MIT
- 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 gradedqualityCmaintenanceEnables AI agents to control a real browser through intent-based tools—reading pages, filling forms, clicking, and replaying self-healing recipes—while returning only concise answers instead of the DOM.MIT
- AlicenseBqualityAmaintenanceControls a real Chrome browser for AI agents, enabling authenticated automation with parallel lanes, token-efficient page reads, and robust recovery mechanisms.12285 npm237MIT
- AlicenseAqualityAmaintenanceEnables AI agents to drive your real, logged-in Chrome browser with existing sessions and cookies, bypassing CAPTCHA and anti-bot measures, with support for multi-session and human-in-the-loop workflows.4046MIT

Cloak Agentofficial
AlicenseAqualityBmaintenanceEnables an agent to run whole browser tasks on live web pages from a plain-language goal — opening tabs, clicking, typing, scrolling, and returning the relevant page sections as markdown — with every step reported alongside its confidence. Tabs can be reused and closed across calls, so multi-step flows continue on the page the previous task ended on.21MIT
TDQS
Scored across 8 tools
Tools are mostly distinct: browser_run creates sessions, browser_observe reads, browser_act performs manual ops, browser_navigate handles within-session navigation, and browser_tabs manages tabs. The main overlap is between browser_resume (handoff continuation/approval) and browser_act (manual element operations), which both act on existing sessions and could occasionally be confused despite clarifying descriptions.
Seven of eight tools follow a clear browser_verb snake_case pattern (browser_run, browser_observe, browser_act, etc.), which is predictable and readable. jev_decide breaks the browser_ prefix convention, but it represents a separate decision-port domain, making the deviation minor and understandable.
Eight tools is well-scoped for a browser automation server with handoff support. Each tool earns its place across the session lifecycle (create, resume, observe, act, navigate, tabs, close) plus one distinct decision tool, with no obvious redundancy or missing role.
The surface covers the full browser session lifecycle: creation (browser_run), continuation (browser_resume), reading (browser_observe), manual action (browser_act), navigation (browser_navigate), tab management (browser_tabs), and teardown (browser_close), plus decision support. Minor gaps exist around multi-session discovery or session listing, but core workflows are fully supported.