MCP Browser Agent

MCPOpen SourceMIT33.1

by ashley-ha • Analytics & Monitoring

A browser automation MCP server that lets Claude-based agents control Google Chrome for web tasks and scripted interactions.

Example Use Cases

1
Automate web interactions (clicking, typing, navigation) in Google Chrome via MCP.
2
Retrieve the browser's planner state and execute sequences of planned actions programmatically.
3
Session recording, interactive element detection, and robust logging/debugging support for browser tasks.

Description

This project implements a Model Context Protocol (MCP) server that provides browser automation capabilities—integrating Claude with Chrome to perform navigation, element interaction, and scripted action execution. It exposes tools to retrieve planner state and execute planned actions, supports session recording, and offers logging and debugging features. Built as an open-source Python utility (MIT licensed) for macOS with Google Chrome, it is suitable for development and automation workflows that require programmatic browser control.

Quick Actions

View on GitHub

Security

Scanned 3 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

D49/100

8/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelFree

Capabilities0 Tools / 0 Prompts / 0 Resources

Ownerashley-ha

CategoryAnalytics & Monitoring

DependenciesGoogle Chromerequired