superagnt Web Scraping MCP MCP server

This official server allows AI agents to scrape websites into clean markdown, perform structured data extraction using JSON schemas, search the web for content, and map site structures. It handles JavaScript rendering and anti-bot measures without requiring a local browser, supporting various output formats like HTML, screenshots, and summaries.

Endpoint and access

OAuth sign-in: the first time you connect, your client opens the vendor's own authorization prompt in a browser.

OAuth sign-inEndpoint checked 2026-10-05Operated by agntdata, inc.

MCP endpoint (Streamable HTTP)

https://mcp.superagnt.com/mcp/web-scraping

Vendor documentation

What you can do with it

Scrape any URL into clean, model-readable markdown
Extract structured data using JSON schemas or prompts
Search the web and retrieve content for results
Map site URLs to discover and scrape relevant pages

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers a Streamable HTTP server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http superagnt-web-scraping-mcp https://mcp.superagnt.com/mcp/web-scraping

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add superagnt-web-scraping-mcp --url https://mcp.superagnt.com/mcp/web-scraping

Cursor

Merge this server into .cursor/mcp.json in your project, then enable superagnt-web-scraping-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "superagnt-web-scraping-mcp": {
      "url": "https://mcp.superagnt.com/mcp/web-scraping"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure). The type must be streamableHttp for a remote HTTP server.

Cline configuration

{
  "mcpServers": {
    "superagnt-web-scraping-mcp": {
      "type": "streamableHttp",
      "url": "https://mcp.superagnt.com/mcp/web-scraping",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start superagnt-web-scraping-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "superagnt-web-scraping-mcp": {
      "type": "http",
      "url": "https://mcp.superagnt.com/mcp/web-scraping"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http superagnt-web-scraping-mcp https://mcp.superagnt.com/mcp/web-scraping

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "superagnt-web-scraping-mcp": {
      "url": "https://mcp.superagnt.com/mcp/web-scraping"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "superagnt-web-scraping-mcp": {
      "serverUrl": "https://mcp.superagnt.com/mcp/web-scraping"
    }
  }
}

See all 957

Do you run superagnt Web Scraping MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing