MCP server

ScrapeGraphAI MCP Server

Extract structured data from pages with a prompt, plus smart crawling. Official: built and maintained by ScrapeGraphAI. It runs locally on your machine over stdio. Setup below for 12 clients (checked 2026-10-25). Repo and registry data checked 2026-10-24.

Maintainer: Official · ScrapeGraphAI
Runs: Local (stdio)
Repo: ScrapeGraphAI/scrapegraph-mcp
GitHub: ★ 117, last push 2026-07-17 (checked 2026-10-24)
License: MIT
Registry: io.github.ScrapeGraphAI/scrapegraph-mcp
Connects to: ScrapeGraphAI
DevHunt: ScrapeGraphAI on DevHunt

Install the ScrapeGraphAI MCP Server

Pick your client. Each tab starts the same local command. Config shapes checked against each client's docs on 2026-10-25.

Run in a terminal. Everything after -- is the command that starts the server. docs

claude mcp add --transport stdio scrapegraphai -- uvx scrapegraph-mcp

Claude Desktop only: Settings > Developer > Edit Config opens claude_desktop_config.json. Add this, save and restart the app. docs

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

Add to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project), or use the install button. docs

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

Add to Cursor

Add to .vscode/mcp.json (note the "servers" key and the type), or use the install button. Command Palette > "MCP: Open User Configuration" for all workspaces. docs

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

Add to VS Code

Run codex mcp add scrapegraphai -- uvx scrapegraph-mcp, or add this to ~/.codex/config.toml. docs

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

Run in a terminal (-s user adds it for all projects; the default is this project). docs

gemini mcp add -s user scrapegraphai uvx scrapegraph-mcp

Run in a terminal; it writes ~/.copilot/mcp-config.json. docs

copilot mcp add scrapegraphai -- uvx scrapegraph-mcp

Add to mcp_config.json: ~/.config/devin/mcp_config.json on macOS and Linux (older installs: ~/.codeium/windsurf/mcp_config.json), %APPDATA%\devin\ on Windows. docs

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

Add to Zed's settings.json (or Settings > AI > MCP Servers > Add Server). Remote servers without an Authorization header sign in with OAuth. docs

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

Add to opencode.json in the project (or ~/.config/opencode/opencode.json). docs

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "scrapegraphai": {
      "type": "local",
      "command": [
        "uvx",
        "scrapegraph-mcp"
      ],
      "enabled": true
    }
  }
}

Add to ~/.kiro/settings/mcp.json (all projects) or .kiro/settings/mcp.json (this project). docs

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

MCP Servers > Configure > Configure MCP Servers opens cline_mcp_settings.json; add this entry. docs

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

Security notes

The local server runs with your user's permissions (uvx downloads it from PyPI on first run).
It reads web pages, and a page can carry prompt-injection instructions. Keep approval prompts on and use a browser profile without your personal sign-ins.

Alternatives

all browser & web scraping MCP servers →

Browser Useofficial · ★ 119k
An agent that drives a real Chrome to finish tasks: fill forms, click through flows, extract data.
Chrome DevToolsofficial · ★ 54k
Control a live Chrome: performance traces, network requests, console and screenshots for debugging.
Playwrightofficial · ★ 39k
Browser automation through the accessibility tree: click, type, navigate and snapshot pages, no screenshots needed.
Skyvernofficial · ★ 23k
AI browser automation in Skyvern's cloud: navigate, fill forms and pull data from any site.
Apifyofficial · ★ 13k
Run any of thousands of Apify scrapers (Actors) for social media, maps, e-commerce and more.
Firecrawlofficial · ★ 7.7k
Scrape, crawl, map and search websites into clean Markdown or JSON.
Bright Dataofficial · ★ 2.7k
Web search and scraping that gets past blocks and CAPTCHAs, with a free monthly quota.
Hyperbrowserofficial · ★ 791
Scrape, crawl and extract with cloud browsers, plus browser-use and Claude computer-use agents.

FAQ

What does the ScrapeGraphAI MCP Server do?+

Extract structured data from pages with a prompt, plus smart crawling.

Is the ScrapeGraphAI MCP server official?+

Official: built and maintained by ScrapeGraphAI.

How do I add ScrapeGraphAI to Claude Code?+

Run: claude mcp add scrapegraphai -- uvx scrapegraph-mcp. Add --scope project to share it with your team through .mcp.json.

How do I use the ScrapeGraphAI MCP server in Cursor or VS Code?+

Open the Cursor or VS Code tab above: it has the mcp.json entry and a one-click install link. Cursor uses the "mcpServers" key; VS Code uses "servers" and needs a type ("stdio").

Does ScrapeGraphAI work in ChatGPT and claude.ai?+

No: it runs locally over stdio, and ChatGPT and claude.ai only connect to remote servers. Use it in Claude Desktop, Claude Code, Cursor, VS Code or another client that can start a local process.

What are the alternatives to the ScrapeGraphAI MCP server?+

Other browser & web scraping MCP servers: Browser Use, Chrome DevTools, Playwright, Skyvern and Apify.

All MCP servers · What is an MCP server? · Agent skills