fetcher-mcp

MCP server for scraping web content using Playwright headless browser.

MCPResearchOpen source

Type: MCP
Transport: http
Open source: Yes
GitHub Stars: ★ 1.1k
Source: mcp-github
Repository: github.com/jae-jae/fetcher-mcp

Overview

Fetcher MCP is an MCP server based on Playwright headless browser, designed for scraping web content. It supports JavaScript execution, intelligent content extraction, multiple output formats, and parallel processing. With Fetcher MCP, AI can easily retrieve and process dynamic web content. Ideal for AI applications requiring information extraction from web pages. Deployment options include command-line installation via npx and Docker deployment.

Capabilities

▪Execute JavaScript to handle dynamic content
▪Intelligently extract main content
▪Support HTML and Markdown output
▪Process multiple URLs in parallel
▪Optimize resource loading to reduce bandwidth usage
▪Robust error handling mechanism

Use cases

Bulk scraping of news articlesExtracting product information for analysisAutomated generation of web page summariesMonitoring website content changes

Setup

Requires: Node 环境Playwright Chromium

npx -y fetcher-mcp or docker run -p 3000:3000 ghcr.io/jae-jae/fetcher-mcp:latest

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How to install Playwright Chromium?

Run `npx playwright install chromium`.

What transmission protocols are supported?

Supports HTTP and SSE protocols.

Related skills

Scrapling

An adaptive web scraping framework capable of handling everything from single requests to large-scale scraping.

MCP

TrendRadar

An AI-driven tool for sentiment monitoring and trend analysis, supporting multi-platform aggregation, RSS subscription, and intelligent notifications.

MCP