Pageport

io.github.CloudCorpRecordsPublished by GitHub account CloudCorpRecordsv0.1.0Updated Oct 29, 2026

Fetch a URL and return its contents as readable markdown text.

VerifiedSTDIODesktop onlyWeb Search & ScrapingFiles & Storage

Overview

AI-generated overview

Fetches a URL over HTTP and returns the page as readable markdown-style text, with paging for long content.

What you can do
  • Fetch a URL and get its contents back as clean markdown-style text, or as the untouched raw document on request.
  • Read long pages in chunks by choosing a start index and maximum length; truncated output reports the offset for the next chunk.
  • Follow redirects with a browser-style request and receive plain-text or other non-HTML bodies unchanged.
  • Get explicit error results with the reason when a host is unreachable or returns an error status.
When to use it
Useful when an assistant needs to read a specific web page as text to scan, quote or summarize it, especially long pages that must be read in pieces. It is a single-purpose fetcher rather than a search or crawling tool.
Requirements
Runs as a local stdio process, either via npx with the npm package or as a Docker container. No accounts, API keys, environment variables or headers are declared. Outbound network access is needed to reach the target URLs.
Before you install
The server sends requests to whatever URL the assistant supplies, so fetched content comes from third parties and may be untrusted or misleading. It only reads pages; no write, send or delete actions are described. No credentials are requested.

Installation

In SourceWeft

  1. Open Pageport in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

pageport

Fetch a web page and read it as text. pageport retrieves a URL over HTTP, turns HTML pages into clean markdown-style text you can scan or quote, and hands non-HTML responses back exactly as they arrive. Long pages are not a problem: ask for a window of characters, then page forward through the rest with an offset.

What it does

  • Sends a normal browser-style request and follows redirects.
  • Converts HTML to readable markdown-style output: headings keep their levels, links keep their targets, lists stay lists, and script or style content is dropped instead of polluting the text.
  • Returns the untouched document when you ask for raw output, and returns plain-text or other non-HTML bodies unchanged.
  • Slices long results: choose where reading starts and how many characters come back. When a result is cut short, the output says so and tells you the offset to use for the next chunk.
  • Reports failures plainly: an unreachable host or an error status comes back as an error result with the reason, never as empty success.

CLI

bash
npx @reneturcios/pageport fetch https://example.comnpx @reneturcios/pageport fetch https://example.com --max-length 2000npx @reneturcios/pageport fetch https://example.com --start-index 2000 --max-length 2000npx @reneturcios/pageport fetch https://example.com --rawnpx @reneturcios/pageport --version

Exit codes: 0 on success, 1 on a fetch error, 2 on a usage error.

MCP server

The same binary runs as a stdio MCP server:

bash
npx -y @reneturcios/pageport mcp

MCP client configuration:

json
{  "mcpServers": {    "pageport": {      "command": "npx",      "args": ["-y", "@reneturcios/pageport", "mcp"]    }  }}

Tool: fetch

Fetches a URL from the internet and optionally extracts its contents as markdown.

ParameterTypeRequiredDefaultMeaning
urlstringyes—URL to fetch
max_lengthintegerno5000Maximum number of characters to return
start_indexintegerno0Start index for content
rawbooleannofalseReturn raw HTML instead of markdown conversion

Docker

bash
docker run -i ghcr.io/cloudcorprecords/pageportdocker run --rm ghcr.io/cloudcorprecords/pageport fetch https://example.com

The container defaults to the mcp subcommand, so a plain docker run -i is a working stdio MCP server.

Development

bash
npm installnpm run buildnpm testnpm run dev

Tests cover the HTML conversion, the slicing and truncation behaviour, and the fetch flow against injected responses — no network is needed.

License

MIT — see LICENSE.

Source: README.md at commit 21266fc

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestOct 29, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts