BrowserPilot

Control a real browser with plain-English instructions, through the Model Context Protocol and Playwright.

A Streamlit app where an LLM (OpenAI or a local Ollama model) plans browsing steps and calls Playwright MCP tools to navigate, click, read and capture pages. It ships with network guardrails and a tool layer that is tested end to end without an LLM. By Madhur Kumar Rana.

View on GitHub CI status Architecture and threat model

This page is a showcase. The agent is not hosted publicly: it needs an LLM key and drives a real browser, so you run it yourself in a few commands.

The interface

Describe a task in plain English; the guardrails run before any browser or model is involved. Below, an instruction aimed at a cloud-metadata address is rejected up front.

BrowserPilot Streamlit interface with example instructions and safety defaults Error shown when an instruction targets a blocked cloud-metadata address

Evidence it works

The screenshot below was captured by the repository's end-to-end test: a real browser, driven through the real Playwright MCP server, on a bundled fictional site. No LLM or internet involved.

Pricing page of the fictional demo site captured by the smoke test
node scripts/mcp_smoke_test.mjs --screenshot docs/assets/screenshot.png
PASS  navigates to home page
PASS  clicks through to pricing
PASS  extracts table rows via evaluate
PASS  takes a screenshot
PASS  default policy blocks loopback origins
All checks passed.

How it works

Streamlit UI→Validation→Agent + LLM→Playwright MCP (pinned)→Chromium

Run it

git clone https://github.com/madhur0770/BrowserPilot.git
cd BrowserPilot
pip install -r requirements.txt
export OPENAI_API_KEY=your-key
streamlit run app.py

Engineering evidence

Known limitations