mcp-server-scraper
v1.0.1by ofershap · author: Ofer Shapira
MCP server for web scraping: extract clean markdown, links, and metadata from any URL.
Package we checked
plugin.json sits at the package root in ofershap/mcp-server-scraper, which is the plugin directory the 1.0.0 spec describes. Its $schema is https://agent-plugins.org/schemas/1.0.0/plugin.schema.json. The manifest lists 1 skill (web-scraping) and 1 MCP server (scraper). Stored mcp.json transports: scraper stdio.
What mcp-server-scraper does, in the publisher's words
Extract clean, readable content from any URL. Returns markdown text, links, and metadata. No API keys, no config. A free alternative to Firecrawl for scraping docs, blogs, and articles.
> Works with Claude Desktop, Cursor, VS Code Copilot, and any MCP client. No accounts or API keys needed.
Demo built with remotion-readme-kit
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 1
- MCP servers
- 1
- Stars
- 6
- License
- MIT
- Repo created
- 2026-02-19
- Last pushed
- 2026-08-10
- Publisher type
- User
- Version
- 1.0.1
Links
Skills · 1
- web-scraping
- Extract clean content from URLs via MCP. Use when the user asks to scrape a URL, read docs/blog/article pages, summarize a link, extract links, search page text, batch-scrape URLs, or get OG/title metadata without Firecrawl.
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
MCP servers · 1
- scraperstdio
- npx -y mcp-server-scraper
Read from the plugin's own mcp.json. We list environment variable names, never values.
Category
Research & Search. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
agent-plugins · mcp · scraper · web-scraping · readability
Related by publisher and keywords
Connect AI coding agents to your real logged-in Chrome via MCP + extension. Not headless. Not a cloud agentic browser.
MCP server for local markdown: search, extract sections, headings, code blocks, and frontmatter.
MCP server for Docker: manage containers, images, logs, exec, and stats from your AI agent.
MCP server for AWS S3: list buckets, browse objects, upload/download, and generate presigned URLs.
Find ready-made scrapers in the Scrape.ly Store, run them in the cloud, and read their results, datasets and logs.
The web as callable functions: search flights across several aggregators, price a part across retailers, and other tasks that only exist behind a live site. The agent reads a typed function library, writes a short script, and Bowmark runs it on the real sites. Bundles the bowmark skill and auto-wires the hosted MCP server.
[](https://agentpluginsdirectory.com/plugins/mcp-server-scraper)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.