Data · Remote MCP server
Scrapi
Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.bamchi/scrapi- Version
- 2.0.6
- Status
- Active
- Category
- data
- Transport
- Streamable HTTP, stdio (local process)
- Package
- npm
- Published
- 2026-02-12
- Updated
- 2026-02-12
- Publisher
- bamchi (GitHub)
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/bamchi) · how
- Repository
- github.com/bamchi/scrapi-mcp-server
- Source
- Registry API entry
Remote endpoints
| Transport | URL | Headers declared |
|---|---|---|
| Streamable HTTP | https://scrapi.ai/mcp | Authorization |
Live check
This directory connected to each remote endpoint and asked for its list of tools. The check connects and lists tools only; it doesn't run tools, sign in or test security.
- Reachable
- Yes (HTTP 200)
- Handshake
- scrapi 3.0.3 · protocol 2025-06-18
- Tools discovered
- 5:
scrape_url,scrape_urls,get_usage,scraper_server_status,get_billing - Checked on
- 2026-10-05
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npm | @scrapi.ai/mcp-server | 2.0.6 | stdio |
How to connect Scrapi
Scrapi is a remote MCP server: there is nothing to install. Its endpoint is https://scrapi.ai/mcp, served over Streamable HTTP. In an assistant that accepts remote MCP servers (often under a setting named connectors, integrations or tools), add a new server and give it this URL; in a client configured by file, add it as a remote (HTTP) server with the same URL.
The registry entry declares an HTTP header for the connection: Authorization. Clients that accept custom headers set it with the server's URL.
It can also run locally from a Node.js package published to the npm registry: @scrapi.ai/mcp-server version 2.0.6. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx - the usual command is npx -y @scrapi.ai/mcp-server@2.0.6. It reads the environment variable SCRAPI_API_KEY (required, secret); set it in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"scrapi": {
"command": "npx",
"args": [
"-y",
"@scrapi.ai/mcp-server@2.0.6"
],
"env": {
"SCRAPI_API_KEY": "<secret>"
}
}
}
}Derived from the registry entry; the live check above only shows whether the endpoint answered. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More data servers
| Server | Runs |
|---|---|
| Scrapeunblocker DfsswgScrapeUnblocker: ScrapeUnblocker allows to bypass anti-bot services and scrape the full page source. | Remote · HTTPLive check: ✓ handshake |
| Scrapeunblocker MCPFetch any web page's HTML or AI-parsed JSON through the ScrapeUnblocker anti-bot API. | Local · stdio |
| Scrapeunblocker MCP RemoteFetch any web page's HTML, AI-parsed JSON, or Google results via the ScrapeUnblocker anti-bot API. | Remote · HTTPLive check: ✓ handshake |
| scrapewrightGive it a URL, get structured rows. A model writes the parser once; replays are free. | Remote & Local · HTTP, stdioLive check: ✓ handshake |
| ScrapingantScrape webpages, handle JavaScript and CAPTCHA, extract structured data. | Local · stdio |
| ScrapingBotPublic web data for AI agents: scrape any page, plus Google, TikTok, Instagram and Amazon as JSON. | Remote · HTTPLive check: ✓ handshake |
| ScrapingdogScrapingdog web-scraping & SERP APIs: web scrape, Google, Amazon, LinkedIn, YouTube, and more. | Local · stdio |
| ScrapingdogScrapingdog MCP - wraps Scrapingdog (scrapingdog.com), a proxy-based web. | Remote · HTTPLive check: ✓ handshake |