WebExtract MCP Server

Any public web page to clean Markdown or fixed-schema JSON for agents. Pay per call, no signup.

Web & Search MIT license Added Oct 27, 2026 Hosted / remote ✓ Verified Oct 27 2 tools

WebExtract is a Web & Search MCP (Model Context Protocol) server: Any public web page to clean Markdown or fixed-schema JSON for agents. Pay per call, no signup. It is MIT-licensed and available as a hosted endpoint, so it works with no local install. It exposes 2 tools including extract_url, page_markdown. Listed on MCP Collection since October 2026.

About WebExtract

Hosted remote MCP server at https://api.webextract.dev/mcp (streamable HTTP, no key needed to connect). Tools: page_markdown returns clean Markdown for any public URL; extract_url returns Markdown plus fixed-schema JSON (article metadata, product/price, tables).
Free tier: 20 calls per day per IP, shared between REST and MCP. JS-heavy pages: /v1/render/extract ($0.008 per call) or /v1/render/markdown ($0.004 per call) on the REST API; each IP gets 5 free renders a day. Failed fetches are not charged.
Paid REST: GET /v1/extract $0.005, GET /v1/markdown $0.002. Unpaid calls return HTTP 402 with x402 USDC options on Base, Polygon, Arbitrum, Avalanche, Optimism, World Chain and Monad. Prepaid credits via Stripe ($1 = 200 credits).
Docs: https://webextract.dev/docs · OpenAPI: https://api.webextract.dev/openapi.json · llms.txt: https://api.webextract.dev/llms.txt

WebExtract tools (2)

Read from the live server on Oct 27, 2026. These are the tools your AI assistant can call once connected.

extract_url
Fetch a public web page (robots.txt respected) and return clean Markdown plus fixed-schema JSON: article metadata, product/price, tables. Free 20 calls/day per IP; pass 'Authorization: Bearer <key>' for prepaid credits.
page_markdown
Fetch a public web page (robots.txt respected) and return clean Markdown only. Cheaper than extract_url (0.4 credit). Free 20 calls/day per IP; pass 'Authorization: Bearer <key>' for prepaid credits.

How to connect WebExtract to Claude, Cursor or VS Code

WebExtract runs as a hosted remote MCP server at https://api.webextract.dev/mcp. Add that URL to your MCP client's config (Claude Code, Cursor, Windsurf or VS Code) and the tools appear immediately, no install required.

{
  "mcpServers": {
    "webextract": {
      "url": "https://api.webextract.dev/mcp"
    }
  }
}

Claude Code: claude mcp add --transport http webextract https://api.webextract.dev/mcp. Servers that require OAuth or an API key will prompt on first use.

WebExtract FAQ

What is WebExtract?

WebExtract is a Model Context Protocol (MCP) server in the Web & Search category. Any public web page to clean Markdown or fixed-schema JSON for agents. Pay per call, no signup. MCP servers expose tools that AI assistants like Claude can call during a conversation.

How do I use WebExtract with Claude or Cursor?

WebExtract runs as a hosted remote MCP server at https://api.webextract.dev/mcp. Add that URL to your MCP client's config (Claude Code, Cursor, Windsurf or VS Code) and the tools appear immediately, no install required.

Is WebExtract free to use?

WebExtract is published under the MIT license, so the software itself is free to run. Hosted or API-backed servers may have their own usage tiers; check the project homepage.

What tools does WebExtract provide?

WebExtract exposes 2 MCP tools: extract_url, page_markdown. This list is read from the live server (last verified Oct 27, 2026).

Is the WebExtract MCP server online?

Yes. MCP Collection checks the endpoint every day; it last answered on Oct 27, 2026.

Where is the source code for WebExtract?

The source is at github.com/nyx464664816-stack/webextract.

More Web & Search MCP servers