Page Fetch MCP

An MCP server provided by OpenKrill that allows AI agents to fetch public web pages and convert them into clean Markdown format, including links and respecting robots.txt rules. It is part of a suite of 62 tools offered by OpenKrill for retrieving live facts and data for AI assistants.

Endpoint and access

No sign-in: your client connects and lists tools immediately, with no account or key.

No sign-inEndpoint checked 2026-10-19Operated by OpenKrill

MCP endpoint (Streamable HTTP)

https://pagefetch.openkrill.app/mcp

Vendor documentation

What you can do with it

Read a web page as Markdown
Fetch app reviews from the US App Store
Retrieve YouTube transcripts
Check X posts and job boards

Tools advertised by the last live check:

fetch_page
extract_page_json
submit_feedback
get_feedback_reply

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 page-fetch-mcp https://pagefetch.openkrill.app/mcp

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 page-fetch-mcp --url https://pagefetch.openkrill.app/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable page-fetch-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "page-fetch-mcp": {
      "url": "https://pagefetch.openkrill.app/mcp"
    }
  }
}

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": {
    "page-fetch-mcp": {
      "type": "streamableHttp",
      "url": "https://pagefetch.openkrill.app/mcp",
      "disabled": false
    }
  }
}

VS Code

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

VS Code configuration

{
  "servers": {
    "page-fetch-mcp": {
      "type": "http",
      "url": "https://pagefetch.openkrill.app/mcp"
    }
  }
}

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 page-fetch-mcp https://pagefetch.openkrill.app/mcp

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": {
    "page-fetch-mcp": {
      "url": "https://pagefetch.openkrill.app/mcp"
    }
  }
}

Windsurf

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

Windsurf configuration

{
  "mcpServers": {
    "page-fetch-mcp": {
      "serverUrl": "https://pagefetch.openkrill.app/mcp"
    }
  }
}

Ground your agent in cited data

Page Fetch MCP gives your agent tools. Koskamo gives it reviewed, cited facts to check its answers against. Add it as a second MCP server; public reads need no API key.

Connect Koskamo Browse datasets

See all 1,282

Do you run Page Fetch 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