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.
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
See and drive the Windows desktop the way the Playwright plugin drives a browser — screenshot and control tree come back with every action — and record the session into a finished demo video with click-zoom, a smoothed cursor and narration.
★not rated 0 18d agoA
tokens not measured
originalMIT
MCP server "bookmyshow-mcp-webscraper" as configured in m0han-r/bookmyshow-mcp-webscraper. Runs locally from the bookmyshow-mcp-webscraper Python package.
Use when the user asks to search Google, do a web search, look something up on Google, or find pages/news/links by running a real Google search. Drives the local Chrome browser over CDP. Falls back to asking the human to solve a CAPTCHA when Google serves a human-verification page.
A tool for extracting Figma Sites and design files into detailed design data and browser-rendered style information. Figma is a design and website-building application; the tool uses a logged-in Chrome browser and a target file.
ToolTrace MCP server — give AI agents a complete web intelligence toolkit. Runs locally from the @tooltrace/mcp-server npm package. Needs 1 environment variable to run.
Lets the agent inspect and automate a live Chrome instance through the DevTools protocol: performance traces, network, console. Runs locally from the chrome-devtools-mcp npm package.
★not rated 0 12d agoA
tokens not measured
originalMIT
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
Operate desktop or browser UI through computer-use-mcp with minimal state-aware tool calls, structured-first targeting, mutually exclusive click locators, bounded vision fallback, and fresh completion evidence. Use when choosing or sequencing computer or browser tools; do not use for implementing the MCP server itself.
MCP server that gives an agent a real browser: url to markdown, screenshot a url, url to pdf. No signup. Runs locally from the pagewatch-mcp npm package. Needs 2 environment variables to run.
A DVR and time-travel debugger for AI browser agents (MCP). Records every session — screen, DOM, network, console, storage — with provenance, so an agent can rewind to the moment it broke and see exactly what happened. Runs locally from the browser-dvr-mcp npm package.
★not rated 0 1mo agoA
tokens not measured
originalMIT
Do things on live websites: look up current prices, check real availability or stock, search a site, get a quote or a fare, drive a configurator, start a booking, or pull anything that only exists behind a form, a filter, or a login. You write a short JavaScript script against typed functions and Bowmark runs it on…
Paid agent tools for secrets, agent configs, diffs, deploy evidence, URL security, web scraping, OG rendering, and funding-rate spreads over x402 on Base, plus a free catalog.
★not rated 0 1mo agoA
tokens not measured
originalMIT
MCP server for browser automation via ZenLink - gives Claude Desktop and other MCP clients native browser control. Runs locally from the zenlink-mcp Python package.
★not rated 0 3mo agoA
tokens not measured
originalMIT