scroll
19 entrées du registre ont été observées exposant un outil nommé scroll — aucun d’entre eux signalé comme capacité privilégiée.
Chaque ligne est le résultat d’une analyse à un instant donné, datée ci-dessous. Forge dispose d’une surface d’outils observée pour 12 342 entrées analysables sur 40 590 (30 %) — une entrée qui n’a pas été analysée ne peut pas figurer ici, l’absence de cette liste n’est donc pas la preuve qu’une entrée n’expose pas cet outil.
- v1.29.2↓ 2k/wk★ 5
Borrow a tab from your own logged-in Chrome, hand it back; 2FA and CAPTCHA stay yours. 66 tools.
ClaudeCursorCopilotGeminimcp - v6.3.0★ 26
Local MCP server for iOS Simulator and macOS app automation with a native Swift bridge
ClaudeCursorCopilotGeminimcp - v0.9.21↓ 148/wk★ 6
Drive your real Chrome browser over MCP — real logins, real cookies. A stdio MCP server (CLI) plus an MV3 extension, driving Chrome via chrome.scripting/chrome.tabs. Multi-tab batch automation, accessibility snapshots, deny-all security by default.
ClaudeCursorCopilotGeminimcpmodel-context-protocolmcp-serverchromechrome-extensionbrowser-automation - v1.1.1★ 5
Zero-dependency macOS desktop automation for AI agents. 18 tools via MCP. macOS 13+.
ClaudeCursorCopilotGeminimcp - v1.0.165★ 338
Real Chrome for agents: start a browser, read pages as numbered markdown, click, type, hand off.
ClaudeCursorCopilotChatGPTGeminimcp - v0.4.0↓ 347/wk★ 1
Arc browser MCP for macOS: agent window, snapshots, DevTools input, guardrails
ClaudeCursorCopilotGeminimcp - v0.5.0↓ 259/wk
MCP server for Android device control via ADB and scrcpy
ClaudeCursorCopilotGeminimcp - v0.3.8↓ 165/wk
Let your AI coding agent test its own frontend work. Connects Claude Code, Cursor, and any MCP client to your real Chrome browser — real sessions, real cookies, no headless conflicts.
ClaudeCursorCopilotGeminimcpbrowserautomationplaywrightthinkrunai-agent - v0.21.0↓ 84/wk★ 3
End-to-end tests without test code. Write one sentence, an agent drives a real browser and returns a verdict, and a passing run is recorded so the next one calls no model. Runs on any URL with no account.
ClaudeCursorCopilotGeminie2e-testingend-to-end-testingtestingtest-automationplaywrightqa - v1.5.9↓ 54/wk★ 5
SideButton MCP server for AI agents — REST API, web dashboard, knowledge packs, and workflow engine
ClaudeCursorCopilotGeminimcpmcp-servermodel-context-protocolai-agentsknowledge-packsworkflow - v0.7.0★ 9
Frontend expert for Claude Code. Screenshots, Lighthouse, axe-core, code analysis, auto-fix.
ClaudeCursorCopilotGeminimcp - v1.1.1★ 5
Open-source MCP server with browser automation and knowledge packs for AI agents
ClaudeCursorCopilotGeminimcp - v0.2.0
A zero-LLM MCP server that replays recorded site maps instead of re-exploring browser routes.
ClaudeCursorCopilotGeminimcp - v0.3.6
Drive your real, logged-in Chrome from any MCP client — even from a remote machine, no inbound port.
ClaudeCursorCopilotChatGPTGeminimcp - v1.0.0
Headless browser primitives for AI agents when sites need real JS rendering.
ClaudeCursorCopilotChatGPTGeminicom.thenextgennexusUnknownil y a 5 moisobservé le · tools/list en directmcp - v1.9.1
Hosted Playwright API for AI agents. Returns a11y trees instead of screenshots.
ClaudeCursorCopilotGeminimcp - v0.4.2
Drive the iOS Simulator via semantic accessibility-tree snapshots. Sub-200ms, no WebDriverAgent.
ClaudeCursorCopilotGeminimcp - v2.0.2
Token-first headless browser for AIs. Extracts a tiny semantic graph, cutting HTML bloat by 95%.
ClaudeCursorCopilotGeminimcp