Connect Feeder to your AI assistant with MCP

Feeder’s MCP server lets Claude, ChatGPT, Cursor, and other Model Context Protocol clients read your feeds, search posts, and manage collections, straight from your account. Here’s how to connect it.

What you’ll need

A Feeder Professional or Enterprise plan.
An AI client that supports MCP.
The server URL: https://feeder.co/mcp

There are no tokens to copy. However you connect, your client sends you to Feeder to log in and approve access.

Option 1: Paste the server URL

Best for clients with a built-in connector screen, like Claude and ChatGPT.

Open your client’s connectors or integrations settings.
Add a custom connector and paste https://feeder.co/mcp.
Log in to Feeder when prompted and approve access.

In Claude this lives under Settings > Connectors. In ChatGPT it’s under Settings > Connectors too, and you may need to turn on developer mode first. Custom connectors are a paid feature in both apps.

Option 2: Paste the config snippet

Best for Claude Desktop and Cursor. Add this to your client’s MCP config file:

{
  "mcpServers": {
    "feeder": {
      "url": "https://feeder.co/mcp"
    }
  }
}

Your client will prompt you to log in to Feeder and approve.

Option 3: Connect from the command line

Best for Codex CLI and Claude Code, where a single command wires up Feeder.

Codex CLI

codex mcp add feeder --url https://feeder.co/mcp
codex mcp login feeder

The login command opens Feeder in your browser, so you can sign in and approve access.

Claude Code

claude mcp add --transport http feeder https://feeder.co/mcp

Then type /mcp inside Claude Code to log in to Feeder and approve.

Manage connected apps

Open Feeder and go to Settings > Account to see everything you’ve connected, and disconnect any app in a click.

What to ask

Once you’re connected, try:

“What are the headlines from my Tech folder today?”
“Find an RSS feed for The Verge and add it to my Mornings folder.”
“Save the three most interesting unread posts to my Read Later collection.”