MCPFax Feed Reader

com.mcpscoresPublished by mcpscores.comv1.0.2Updated Oct 24, 2026

What a source published since you last looked, from any RSS, RDF or Atom feed.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

A remote MCP server that fetches and normalizes RSS, RDF and Atom feeds, discovers a site's feeds, and collects requests for data sources.

What you can do
Read any RSS, RSS/RDF or Atom feed and get items in one consistent shape: title, link, ISO-8601 date, author, summary and categories, plus feed title and last-build time. Discover the feeds a site declares in its HTML head, with conventional locations suggested as guesses when none are declared. Describe in your own words what data you want and learn whether a supplying service exists, with its MCP endpoint. View an aggregate of what agents have requested, most-requested first, including categories nothing yet serves.
When to use it
Use it when you need recent items from a site's feed in a uniform format, when you know a site publishes updates but not where its feed lives, or when you want to check whether a data source you need is already offered.
Requirements
Remote streamable HTTP endpoint; no authentication, environment variables or headers declared. Network access to the endpoint and to the feeds being read. The discover_feeds tool is listed as costing $0.005 USDC per call.
Before you install
discover_feeds is described as costing $0.005 USDC per call, so calls may involve payment. request_data sends your description of the wanted data to the operator and is catalogued, though the tool states nothing identifying is stored. Feed content is fetched from third-party sites.

Installation

In SourceWeft

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

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.mcpscores%2Ffeed-reader/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "mcpfax-feed-reader": {
      "type": "http",
      "url": "https://feed-reader.bowling-anthony.workers.dev/mcp"
    }
  }
}

Tools

4

request_data

Tell us what data you are looking for (free)

FREE, no payment. Describe in your own words the data you are trying to buy — anything, not just feeds — and get back whether we operate a service that supplies it, with the MCP endpoint if so. Every request is catalogued so repeatedly-requested data gets built. Nothing identifying is stored, only the words of the request.

Parametersneedrequired

demand_report

What agents are asking for most (free)

FREE, no payment. The aggregate of what agents have told us they are looking for, most-requested first, with the categories nothing available yet serves.

Parametersdays

read_feed

Read an RSS or Atom feed as structured items

Fetch any RSS, RSS/RDF or Atom feed and get back one consistent shape: title, link, ISO-8601 publication date, author, summary and categories per item, plus the feed's own title and last-build time. The three feed dialects disagree about every element name and date format; this normalises them so you never branch on feed type. Pass 'since' to return only items published after a timestamp — the cheap way to poll for what changed. Costs $0.005 USDC per call via x402 on Base.

Parametersurlrequiredlimitsince

discover_feeds

Find the feed for a website

Given a site's normal URL, return the feeds it declares in its HTML head, each with title and type. Use when you know a site publishes updates but not where its feed lives. If the page declares none, conventional locations are suggested and clearly marked as guesses that may 404. Costs $0.005 USDC per call via x402 on Base.

Parametersurlrequired

Version history

1
  1. v1.0.2LatestSep 16, 2026

Score

83% 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 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.