Skip to content
MCP server

Pagemd

Fetch any public web page as clean Markdown with its title, byline, date and JSON-LD

Install
Pricing
Paid
Platforms
API
Runs
Remotely
Version
0.2.0
Listing updated
1 day ago

About Pagemd

Pagemd is a paid MCP server for web search and scraping. It runs as a hosted remote server, so there is nothing to install locally.

Pagemd gives an agent a page's main content with headings, lists, tables, code and absolute links intact, minus navigation, banners and footers. It also returns what the page says about itself: title, canonical address, language, author, date, description, word count and JSON-LD. Author and date come only from the page's own meta tags, structured data or marked-up byline, and stay empty when absent rather than being inferred.

Pages are read and never executed. Addresses resolving to private, loopback or cloud-metadata networks are refused at connect time and on every redirect. It makes one page per request, at most one request per second to any site, keeps no cookies and uses an identifiable user agent.

Agents pay per request in USDC over x402 with no account. Unreadable addresses, non-HTML files and client-rendered pages with no server-side text are refused and not charged. Initialize and tools/list are free, and the tool is read_page.

Install

Run in a terminal

claude mcp add --transport http pagemd https://pagemd.kaneky.dev/mcp

Add to Settings → Connectors → Add custom connector

https://pagemd.kaneky.dev/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "pagemd": {
      "url": "https://pagemd.kaneky.dev/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "pagemd": {
      "type": "http",
      "url": "https://pagemd.kaneky.dev/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "pagemd": {
      "serverUrl": "https://pagemd.kaneky.dev/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "pagemd": {
      "type": "http",
      "url": "https://pagemd.kaneky.dev/mcp"
    }
  }
}

Tools this server provides (1)

Taken from the project documentation; the running server may differ.

read_page
Reads a public web page as Markdown with its metadata.

What it does

Clean Markdown
Main content with structure preserved and chrome removed.
Page metadata
Title, canonical URL, language, byline, date and JSON-LD.
Stated facts only
Author and date stay empty when the page does not say.
Network safety
Private and metadata addresses are refused, even via redirects.
Polite fetching
One request per second per site, no cookies.
Charged for success
Unreadable pages are refused free.

Good for

  • Feed a web article to an LLM as Markdown
  • Extract a page's structured data
  • Read documentation pages in an agent loop
  • Check an article's stated author and date

Pricing

Paid

Pay per request in USDC over x402

Prices change. Check pagemd.kaneky.dev before you buy.

Pagemd FAQ

How is it priced?

Per request in USDC over x402; the page does not state the amount.

Does it run JavaScript?

No. Pages are read, never run, and client-rendered pages with no text are refused.

What is free?

Initialize and tools/list; refused requests are not charged.

Are missing authors guessed?

No. Fields stay empty when the page does not state them.

Is Pagemd free?

No. Pagemd is a paid product.

How do I add Pagemd to Claude Code?

Run this command in your terminal: claude mcp add --transport http pagemd https://pagemd.kaneky.dev/mcp

What are the best alternatives to Pagemd?

The closest alternatives to Pagemd are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and AI-Powered directory.

Alternatives to Pagemd

  1. MCP server for AI clients to scrape sites with HTTP and stealth browser sessions

    Runs locally
    • 17 tools
    • Open source
    • 104K GitHub stars
    • Web search and scraping
  2. MCP server that lets AI agents search, scrape and interact with web pages

    • 3 tools
    • Remote
    • Freemium
    • 7.8K GitHub stars
    • Web search and scraping
  3. SearXNG Search

    MCP server

    MCP server for web search and page reading through a SearXNG instance

    Runs locally
    • 3 tools
    • Open source
    • 1.4K GitHub stars
    • Web search and scraping
  4. NeuralVerge

    MCP server

    Structured, source-tagged business and people data from 300+ sources for agents

    • 200 tools
    • Remote
    • Free trial
    • 1 GitHub star
    • Web search and scraping
  5. Search AI tools, agents and MCP servers and get install configs from inside your AI assistant.

    • 4 tools
    • Remote
    • Free
    • Developer tools
  6. Hosted MCP server that returns any Shopify store's products, prices and stock

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • E-commerce