7,062 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Stealth Chromium MCP server with hybrid AOM + Set-of-Mark vision and Readability extraction. Runs locally from the stealth-agent-browser-mcp npm package. Needs 6 environment variables to run.
★not rated 1 5mo agoA
tokens not measured
originalApache-2.0
Governed, semantic tools for driving the user's real browser: navigate, inspect, find, click, fill, type, screenshot, record. Local by construction, with optional policy and audit.
★not rated 1 yesterdayA
tokens not measured
originalApache-2.0
MCP server "browser-use-claude-mcp" as configured in jasondsmith72/Browser-use-claude-mcp. Runs dist/index.js with node. Needs 9 environment variables to run.
★not rated 1 1y agoA
tokens not measured
originalMIT
MCP server connector for IHG Hotels (Holiday Inn, InterContinental, etc.) using Playwright browser automation. Runs locally from the @striderlabs/mcp-ihg npm package.
Audit live web pages for fake/mock data — 5-phase Playwright + Claude Code skill that classifies every visible value as REAL, MOCK, LLM, HARDCODED, BROKEN, or UNKNOWN.
★not rated 1 4mo agoA
tokens not measured
originalMIT
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Use when asked what a product can do, to generate or refresh a use-case panel, to build a demo deck, or to find features that exist in code but are unreachable in the app. Walks the codebase AND the live app in a browser; only browser-verified use cases are cataloged.
Execute sensitive browser actions (login, payments, form filling) outside the core agent loop using a dedicated CLI tool. Use when Claude needs to handle credentials, payment information, or other sensitive data in browser automation workflows. Triggers when users ask to log into websites, fill payment forms, or…
Browser MCP server that connects to your existing browser — your sessions, passwords, and extensions preserved. Runs locally from the @lautrek/scout npm package.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Local MCP server for AI agents: local YOLO-based UI-element detection (OmniParser-v2 icon detector) with per-element OCR, hash caching, and full keyboard / mouse / screen / clipboard control via pyautogui + mss. Runs locally from the kira-mcp Python package.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Instagram downloader — CLI + MCP server. Six tools, three prompt templates, session capture against your real browser profile via the Chrome M144 chrome://inspect toggle.
★not rated 1 4mo agoA
tokens not measured
originalMIT
An agent driving a browser tends to start a new one rather than use the one already open, and to size its work off the core count. This warns once per session when a tool payload is about to do either. Never blocks.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Safely retrieve readable text from one public URL for SimonOS. Use when a user sends a single http(s) link and asks to read, summarize, or inspect it; return a clear limitation for private or unsupported social sources.
Skill "agent-browser" from skytiger6724/gemini-skills, covering browser automation with agent-browser, core workflow, command chaining, chain open + wait + snapshot in one call and chain multiple interactions.
Drive a live web app as a source-blind, naive first-time user and report UX/behavior gaps (bugs, broken expectations, UX surprises, a11y) before deploy. Config-driven, Playwright-MCP powered.
★not rated 1 1mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: