7,087 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.
Use this skill when the user is building, securing, or auditing a browser-based AI agent (Playwright, Puppeteer, Stagehand, browser-use, or custom browser automation). Triggers on requests to "secure my browser agent", "detect prompt injection in web pages", "block my agent from visiting bad URLs", "scan this page for…
Pay-per-call MCP server. $0.01 USDC extracts schema.org/Product JSON from any URL via x402. Runs locally from the x402-extract-mcp npm package. Needs 1 environment variable to run.
Extract and process web content into clean, structured formats optimized for LLMs. Runs locally from the @agenson-horrowitz/web-content-extractor-mcp npm package.
★not rated 0 5mo agoA
tokens not measured
originalMIT
Your AI-powered personal desktop assistant — MCP server for Gmail, Calendar, files, clipboard, apps, browser, and more. Runs locally from the personal-mcp-arun Python package. Needs 1 environment variable to run.
Browser-side debug layer that exposes live PWA state (DOM, framework state, stores, events, library popups) to AI agents via MCP — eliminating the human copy/paste loop when debugging web apps with AI.
★not rated 0 2mo agoA
tokens not measured
originalMIT
Easily create reusable automation tools from casual browser actions using Apify Agent. Runs locally from the codify-mcp npm package. Needs 1 environment variable to run.
★not rated 0 7mo agoA
tokens not measured
originalMIT
Lets the agent inspect and automate a live Chrome instance through the DevTools protocol: performance traces, network, console. Runs locally from the @dinesh-nalla-se/chrome-devtools-mcp npm package.
★not rated 0 9mo agoA
tokens not measured
forkApache-2.0
Runs an end-to-end test from a Jira ticket number. Reads the ticket, executes the browser test steps it contains with Playwright, optionally scores any AI or text output with the RetriEval MCP, and writes a pass/fail result back to the ticket. Use this WHENEVER the user gives a ticket key and asks to test, verify, QA…
Goal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots. Runs locally from the cowork-qa-mcp npm package. Needs 2 environment variables to run.
MCP server connector for Chick-fil-A — search menu, nutrition, locations, orders, and rewards via browser automation. Runs locally from the @striderlabs/mcp-chickfila npm package.
Lets OpenClaw agents discover and invoke WebMCP tools exposed by websites via Chrome's navigator.modelContext API. Instead of clicking buttons and scraping DOM, the agent calls structured tools directly.
Scrape public Instagram data without logging in and without a Meta developer account — profiles, posts, reels, stories, comments, hashtags, locations, and mentions. Use when the user wants to fetch an Instagram profile's follower count, bio, or post count, pull a profile's recent posts or reels, read the comments on a…
Scope coverage, build a testing strategy, test the feature with agent-browser, capture screenshots/video (always mandatory), upload to S3, and create a structured test report (never skip).
MCP servers exposing SeleniumBase as tools for MCP clients. Runs locally from the seleniumbase-mcp Python package.
★not rated 0 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: