DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to run a web browsing agent in a local chat window with Invisible Playwright MCP

Start the standalone web UI with your OpenRouter key and type a browsing task on the left, watch the browser on the right.

Authorization notice. Invisible Playwright MCP is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Credentials. Passing the key as a command flag stores it in shell history and, on Linux, in the process list, so keep it in a .env file or the environment instead.

Who it is forA non-developer or someone without an MCP-capable assistant who wants to ask an agent to browse a site and see what it does.

The problemMost AI chat tools cannot open a live browser, so tasks that need real page interaction are left undone.

The outcomeA local chat page at 127.0.0.1:8765 where the agent answers your request and the live browser is visible beside the chat.

What you need first

  • uv installed, using the install command for your operating system from the README
  • An OpenRouter API key for the standalone web UI and for model calls
  • An MCP-capable assistant such as Claude Code, Codex or Gemini CLI, for the MCP route
  • Permission to automate the sites you point it at, and a read of their terms

Steps

  1. Install uv with the README command for your system, for example curl -LsSf https://astral.sh/uv/install.sh | sh on Linux.
  2. Put your key in a file named .env in the folder you run from, as OPENROUTER_API_KEY=sk-or-..., so it stays out of your shell history.
  3. Run uvx invisible-playwright-mcp ui from that folder.
  4. Open http://127.0.0.1:8765 in your browser.
  5. Type a task such as checking a page for a specific piece of information, then read the answer and the live page side by side.

Prompt for your agent

Using the invisible-playwright-mcp web UI from feder-cr/invisible_playwright_mcp, send this task to the agent: <task describing the page and the information wanted at <target-url>>. Expected output: the agent's answer in the chat, with the browser showing the page it read. Verify that the answer names the source page and does not guess any value the page did not show.

Caveat. The web UI sends the conversation and what the agent reads on the page to OpenRouter under your key, so do not browse pages whose contents you would not share with that provider.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page