MCP Browser Automation

MCPOpen SourceMIT29.1

by Cam10001110101 • Workflow & Task Management

An MCP server that lets AI agents control Playwright browsers using locally-hosted Ollama models for automated web interaction, data extraction, and session management.

Example Use Cases

1
Navigate websites and perform interactive tasks (search, form submission, clicking) using local LLMs without external API calls.
2
Extract structured data or full-page content and DOM structure for summarization, scraping, or analysis.
3
Automated screenshotting, session management, and reproducible browser workflows for testing or research.

Description

This repository implements a Model Context Protocol (MCP) server that enables AI-driven browser automation via Playwright integrated with local Ollama models. It exposes tools for launching browsers, clicking, typing, scrolling, extracting page content and DOM structure, taking screenshots, and managing sessions. The system supports interactive feedback loops, conversation history, file-based tasks, and deterministic outputs for reproducible automation. It's geared toward privacy-conscious, local execution of agent-driven web workflows like scraping, research, and automated testing.

Quick Actions

View on GitHub

Security

Scanned 3 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

OwnerCam10001110101

CategoryWorkflow & Task Management

DependenciesStandalone