MCP server · Research

Feedbagel MCP server

Let your AI search the Feedbagel RSS catalog, follow feeds, and send new entries to webhooks for you.

This is a small helper that connects your AI assistant to Feedbagel, a service for finding and following RSS feeds. Once it is set up, you can just ask your AI in normal words to search for feeds, follow them, or set up alerts. It is handy if you keep an eye on blogs, news sites, or podcasts and want your AI to do the clicking around for you.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to an app. This one connects your AI to Feedbagel, so it can look up feeds and manage your follows there. You ask in plain words, and the helper does the actual work behind the scenes.

What this MCP server does

You ask your AI something like find feeds about a topic, or follow this blog for me. Your AI passes that request to this helper program. The helper talks to Feedbagel over the internet using your account key. Feedbagel sends back the matching feeds, entries, or confirms the change. Your AI then shows you the result in the chat in normal language.

Flow diagram: you ask your AI “Find feeds about climate tech”, the Feedbagel MCP server connects it to Feedbagel, and you get back feeds, entries, and confirmations.

Click to zoom

What you can do with it

Search the Feedbagel catalog for feeds by keyword
Find feeds that live on a particular website
See the title, favicon, and feed list for a site
Follow a feed and unfollow it later
List the feeds and webhooks you are following
Create, pause, resume, or delete webhooks
Read recent entries from a feed, and open a single entry

Try asking your AI

“Search Feedbagel for feeds about climate tech”
“What feeds are on theverge.com?”
“Follow the feed at example.com/rss for me”
“Show me the latest entries from my followed feeds”
“Set up a webhook that sends new entries to this address”

What it gives back to you

You get answers in the chat: lists of feeds with their titles and addresses, recent entries with titles and links, or a short note confirming that a follow or webhook was added or removed. Single entries come back as their title, link, and content. Everything is shown as text you can read, not as files or code.

Before you start

What you need

A Feedbagel account
An API key from your Feedbagel dashboard (pick the Agent scope; it is like a password for apps)
An MCP client such as Claude Desktop, Cursor, or Windsurf
Node.js installed on your computer if you run it with npx

Good to know

It can change your account: it can follow and unfollow feeds and create or delete webhooks, so check before letting your AI make changes you did not mean.

Install it with your AI

Add Feedbagel MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Feedbagel MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.