scrapi
Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.
Open the source (opens github.com) https://github.com/bamchi/scrapi-mcp-server
Before you use it
- Runs on someone else's server: what you send it leaves your machine.
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
- Needs credentials: SCRAPI_API_KEY. Use a key with the least access you can.
What it is
MCP servers from io.github.bamchi.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
npm package (stdio)
@scrapi.ai/mcp-server@2.0.6
From the server's entry in the official MCP Registry
Remote endpoint (streamable-http)
https://scrapi.ai/mcp
From the server's entry in the official MCP Registry
Settings it asks for
SCRAPI_API_KEYsecret required · Your Scrapi API key (get one free at https://scrapi.ai/dashboard)
Related
-
Scrapingant
MCP serversScrapingAnt MCP — wraps the ScrapingAnt web scraping API (scrapingant.com)
@pipeworx/mcp-scrapingant@0.2.1 -
Scrapingbee
MCP serversScrapingBee MCP — wraps the ScrapingBee headless-scraping API (scrapingbee.com)
@pipeworx/mcp-scrapingbee@0.2.1 -
Scrapingdog
MCP serversScrapingdog MCP — wraps Scrapingdog (scrapingdog.com), a proxy-based web scraping API with…
@pipeworx/mcp-scrapingdog@0.2.1 -
ScrapingBee
MCP serversScrape any web page, search Google/Amazon/Walmart/YouTube and extract data via the ScrapingBee API.
-
Scrapingdog
MCP serversScrapingdog web-scraping & SERP APIs: web scrape, Google, Amazon, LinkedIn, YouTube, and more.
scrapingdog-mcp@0.1.1 -
Scrapiq
MCP serversAny URL to clean text, markdown, or JSON for LLM/RAG pipelines.