How do I install the pyscrappy mcp server?

Use a recorded configuration for your client, replace example credential values and paths, and verify the documented runtime. Restart or reconnect the client, then inspect the available tools.

What credentials does it need?

The recorded environment keys are `OMDB_API_KEY`. Keep credentials outside committed files and confirm the configuration required by your installed version.

SSyncDev

Start a project

PyScrappy MCP Server

Web-scraping toolkit with 22 tools for structured web data as JSON for AI agents.

Local serverstdioPython

What is the PyScrappy MCP Server?

Web-scraping toolkit with 22 tools for structured web data as JSON for AI agents.

What you get

PyScrappy is an AI-native web scraping toolkit that turns websites into structured, LLM-ready data. Use it as a Python library or expose it as an MCP server for AI agents.

Generic scraper — — give it any URL, get back structured text, links, images, tables, and metadata
LLM-ready output — — .to_markdown() turns any result into clean Markdown; also .to_json() and .to_dataframe()
MCP server — — expose the scrapers as tools for AI agents (Claude, Cursor, local LLMs, …)
JS rendering — — optional Playwright backend for JavaScript-heavy sites
Custom selectors — — pass CSS selectors to extract exactly what you need
Concurrent scraping — — scrape_many / scrape_all run scrapes in parallel

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

Tool	What it does
scrape_url	Scrape any URL — text, links, images, tables, metadata
scrape_wikipedia	Fetch a Wikipedia article (full / paragraphs / headers)
scrape_stock	Yahoo Finance quotes, history, and profiles
scrape_news	RSS/Atom feeds, auto-discovered site feeds, or a single article
search_images	Image search (returns URLs + metadata)
search_youtube	YouTube video search
search_linkedin_jobs	Public LinkedIn job listings
search_github	GitHub repository search (stars, language, …)
search_hackernews	Hacker News story search (points, comments)
search_books	Book search via Open Library (title, author, year)
get_weather	Current weather for a place (no key)
get_crypto	Cryptocurrency prices and market data (CoinGecko)
convert_currency	Exchange rates and currency conversion
define_word	Word definitions and examples

How to install the PyScrappy MCP Server

{
  "mcpServers": {
    "pyscrappy": {
      "command": "pyscrappy-mcp",
      "env": { "OMDB_API_KEY": "your-key" }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

Variable	Description	Required
OMDB_API_KEY	Credential the server authenticates with.	Yes

Example prompts to try

“Use PyScrappy to scrape url.”
“Use PyScrappy to scrape wikipedia.”
“Use PyScrappy to scrape stock.”

Frequently asked questions

Web-scraping toolkit with 22 tools for structured web data as JSON for AI agents. Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.