MCP Browser Agent

MCPOpen SourceMPL-2.042.3

by imprvhub • Automation & Orchestration

Provides Claude Desktop with autonomous headful browser automation and API request capabilities via a Model Context Protocol (MCP) server.

Example Use Cases

1
Automate real browser interactions (navigation, clicks, form filling, dropdown selection) in a headful Playwright session.
2
Capture visual evidence and debugging context by taking full-page or element screenshots and accessing browser console logs.
3
Perform HTTP API requests (GET/POST/PUT/PATCH/DELETE) and chain those calls with browser automation to implement multi-step workflows.

Description

MCP Browser Agent is an MCP integration that exposes a persistent Playwright-powered browser to Claude Desktop, enabling navigation, DOM interactions, screenshots, JavaScript execution, and HTTP API requests. It captures browser console logs and stores screenshots as MCP resources, supports chained multi-step workflows, and offers detailed error information for recovery. The agent is designed for technical automation tasks and debugging workflows where an AI needs real browser state and visual outputs.

Quick Actions

View on GitHub

Security

Scanned 2 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

D44/100

4/17 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

Ownerimprvhub

CategoryAutomation & Orchestration

DependenciesStandalone