Scrapegraph MCP Server

by scrapegraphai Your server? Claim it

local only

Scrapegraph MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 158 installs a week from pypi. Last commit 17 Jul 2026.

AI-powered web scraping and data extraction capabilities through ScrapeGraph API

Installs per day peak 49 · avg 26 · -25% w/w

a month agotoday

158

Installs / week

pypi · scrapegraph-mcp

119

Stars

5 open issues

17 Jul 2026

Last commit

from GitHub

MIT

License

Python

Nothing serious here today

Today is the operative word: we check Scrapegraph MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add scrapegraph-mcp -- uvx scrapegraph-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "scrapegraph-mcp": {
      "command": "uvx",
      "args": [
        "scrapegraph-mcp"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.scrapegraph-mcp]
command = "uvx"
args = ["scrapegraph-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "scrapegraph-mcp": {
      "command": "uvx",
      "args": [
        "scrapegraph-mcp"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "scrapegraph-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "scrapegraph-mcp"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: SGAI_API_KEY (Your ScapeGraph API key (optional - can also be set via MCP config)).

Alternatives to Scrapegraph MCP

same job, measured the same way

Researchsearch

by cloudcorprecords

Web search, page extraction, crawling, and site mapping powered by the Tavily API.

local only

Fuze Data Tools

by fredxhansson-cmyk

No-code web scraping & data-extraction Apify actors: scrape and enrich web data at scale.

95 tools answering

HasData Web Scraping

by hasdata

Fetch any public web page through managed proxies, with optional JS rendering and extraction rules.

111 installs/wk 1 tools answering

Thunderbit MCP Server

by thunderbit-open

AI-powered web scraping MCP. Distill pages to Markdown or extract structured data via JSON Schema.

65 installs/wk local only

Thunderbit MCP Server

by thunderbit-com

AI-powered web scraping MCP. Distill pages to Markdown or extract structured data via JSON Schema.

local only

Irmu — Web Data MCP

by polgoide

Web scraping, browser automation, screenshots and AI data extraction for AI agents via MCP.

answering

Scrapingant

by mcparmory

Scrape webpages, handle JavaScript and CAPTCHA, extract structured data

217 installs/wk local only

pline.ai

by grepsr

Scrape, crawl, batch-scrape, map, and search the web through the hosted pline.ai API.

304 installs/wk local only

Scrapegraph MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for Scrapegraph MCP?

Scrapegraph MCP runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package scrapegraph-mcp was installed 158 times last week.

How do I connect Scrapegraph MCP?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls scrapegraph-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use Scrapegraph MCP?

The pypi package scrapegraph-mcp was installed 158 times in the last week. Week over week that is -25%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Scrapegraph MCP open source?

Yes — it is published under the MIT licence, written in Python, 119 stars on GitHub and 5 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.