Web Scraper MCP Server

MCPOpen Source10.0

by snd-primary • Documentation & Docs

An MCP server that scrapes MDN web documentation and exposes it to Claude Desktop for easy querying and summarization.

Example Use Cases

1
Fetch and summarize MDN documentation pages (https://developer.mozilla.org) to provide concise API or language feature explanations.
2
A lightweight, dependency-free MCP endpoint to avoid transport/uvicorn dependency issues when integrating with Claude Desktop.
3
A full-featured scraper endpoint (FastAPI-based) to extract title, content text, original URL, and source metadata for downstream indexing or QA.

Description

This project implements a ModelContextProtocol (MCP) server in Python to scrape MDN web docs and return document title, content text, original URL, and source info. It offers both a full-featured implementation (FastAPI, httpx, BeautifulSoup) and a lightweight variant using only the Python standard library for environments where external dependencies cause issues. The server is designed for seamless integration with Claude Desktop and includes troubleshooting guidance for common errors.

Quick Actions

View on GitHub

Security

Scanned 2 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

D40/100

3/17 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

Ownersnd-primary

CategoryDocumentation & Docs

DependenciesStandalone