mcpField
W
Web Extract MCP Server

Web Extract MCP Server

Remote
github.comBrowser Automation0Updated 5d ago

About Web Extract MCP Server

A hosted MCP server for agents retrieving web pages and sitemap data. It offers capped previews and paid full endpoints for extraction, monitoring, and sitemap access.

Key features

  1. 01Clean Markdown URL previews
  2. 02Prompt-injection screening
  3. 03First 20 sitemap URLs
  4. 04Paid extraction and monitoring endpoints

Use cases

  1. 01Preview a page before retrieval
  2. 02Discover URLs listed in a sitemap
  3. 03Monitor pages for changes
  4. 04Retrieve full web content

MCP support

Exposes a streamable HTTP MCP endpoint with free preview tools and paid endpoints for web extraction, monitoring, and sitemap access.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://jobs.greyridgesignals.ai/mcp/web
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Web Extract MCP Server

Hosted MCP server (streamable HTTP) for web retrieval by agents.

Endpoint: https://assetfactory-jobs-x402.sigrunner.workers.dev/mcp/web

Free tools:

  • web_extract_preview - capped clean-markdown extraction of a URL, with a prompt-injection screen.
  • sitemap_preview - first 20 URLs from a site's sitemaps.
  • get_premium_access - how to call the full paid endpoints.

Paid endpoints (x402, USDC on Base, no signup): /web/extract, /web/monitor, /web/sitemap at $0.003 per call. Docs: https://jobs.greyridgesignals.ai/llms.txt

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.