Feedport

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

Fetch and parse RSS or Atom feeds from a URL.

VerifiedSTDIODesktop onlyWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Fetches and parses RSS 2.0 or Atom feeds from a URL, returning channel metadata and a clean list of items instead of raw XML.

What you can do
  • Fetch a whole feed: title, link, description and its items
  • Fetch only the item list, optionally capped with a limit
  • Validate an address and report whether it is a usable feed, its format and item count
  • Decode CDATA sections and XML entities and normalize Atom entries into the same item shape
When to use it
Useful when an assistant needs to read news or blog feeds, summarize recent posts, or check whether a given URL is actually a feed before relying on it. It is a small, single-purpose reader rather than a general web scraper.
Requirements
Runs as a local stdio process, either via npx with the npm package or via the container image; the MCP server is started with the mcp subcommand. No accounts, API keys or environment variables are declared. Network access to the feed URLs is required.
Before you install
The assistant can make the machine fetch arbitrary URLs supplied in a request, so only point it at feeds you trust. Feed content is third-party text and may contain misleading or injected instructions. No credentials or write actions are involved.

Installation

In SourceWeft

  1. Open Feedport 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

feedport

feedport reads web feeds for you. Give it the address of an RSS 2.0 or Atom document and it hands back the feed's title, link and description plus a clean list of its items — titles, links, descriptions, dates and ids — without you having to look at raw XML. It can also check an address first and tell you whether what lives there really is a feed.

Install

bash
npx @reneturcios/feedport validate-feed https://example.com/feed.xml

Or run the container image:

bash
docker run -i ghcr.io/cloudcorprecords/feedport

The container defaults to the MCP server (see below). Pass CLI arguments to use it as a CLI instead.

CLI

All commands print JSON.

bash
# Whole feed: channel metadata plus itemsfeedport fetch-feed https://example.com/feed.xml
# Just the items, at most five of themfeedport fetch-feed-items https://example.com/feed.xml --limit 5
# Is this address actually a feed?feedport validate-feed https://example.com/feed.xml# {"valid": true, "format": "rss", "item_count": 12}
feedport --version

Exit codes: 0 on success, 1 when a feed cannot be fetched or parsed (the error names the problem), 2 for usage errors.

MCP server

One bin serves both faces. The mcp subcommand starts a stdio MCP server:

bash
npx -y @reneturcios/feedport mcp

MCP client configuration:

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

Tools

ToolInputWhat it returns
fetch_feedurl (string, required), limit (integer, optional)The feed's title, link and description, plus items — each with title, link, and description, pubDate and guid when the document carries them.
fetch_feed_itemsurl (string, required), limit (integer, optional)Only the item list, in the same shape as fetch_feed's items.
validate_feedurl (string, required)valid, the detected format (rss, atom or unknown), the item_count, and an error string when the address is not a usable feed.

RSS 2.0 items come from <item> elements and Atom entries from <entry> elements; for Atom, an entry's summary (or content) becomes its description, its published (or updated) date becomes pubDate, and its id becomes guid. CDATA sections and XML entities are decoded.

Development

bash
npm installnpm run build   # tsc -> dist/npm test        # node test runner over test/*.test.ts, no networknpm run dev     # run the CLI from source via tsx

License

MIT — see LICENSE.

Source: README.md at commit e4cd3ce

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