# AgentFeed

> AgentFeed is a freemium MCP server for web search and scraping. MCP server and REST API that turn RSS/Atom feeds into JSON and web pages into clean text. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** API, self-hosted
- **Website:** https://agentfeed.bigfloppy.net
- **Repository:** https://github.com/wminno/agentfeed
- **MCP Registry name:** net.bigfloppy.agentfeed/agentfeed
- **Categories:** web search and scraping
- **Listing updated:** 2026-11-14

## About

AgentFeed is a very small service with two jobs: parse a feed or pull the readable text out of an article. Feed results come back as flat entries with title, link, published date and a summary cut to 500 characters, and article results carry title, author, text and markdown, with text capped at 20,000 characters. The same pipeline is available as plain GET endpoints (/api/feed and /api/article) and as a Streamable HTTP MCP endpoint at /mcp.

The free tier is 3 URLs a day per IP address with no key, or a free trial key of 50 requests a day with no email. A paid key costs $5 per 100,000 requests with no rate limit and is valid for a year, paid by card or USDC on Base. Keys are sent in an X-Api-Key header.

The code is MIT licensed, runs as a single stateless Python process, and can be self-hosted. Outbound fetches are capped at 2 MB and 15 seconds, and the README describes them as SSRF-safe. The site says it was built by an autonomous agent.

## Features

- **Feed to JSON:** Parses any RSS or Atom URL into flat entries.
- **Article extraction:** Returns title, author, text and markdown for a page.
- **Dual interface:** Available as MCP tools and as simple GET endpoints.
- **Capped outputs:** Summaries are cut to 500 characters and article text to 20,000.
- **Self-hostable:** MIT-licensed Python server with no database.

## Good for

- Feed an agent the latest items from a blog or news feed
- Pull readable text from a news page for summarising
- Monitor several feeds without writing a parser
- Run a private copy for internal content pipelines

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http agentfeed https://agentfeed.bigfloppy.net/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://agentfeed.bigfloppy.net/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "agentfeed": {
      "url": "https://agentfeed.bigfloppy.net/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "agentfeed": {
      "type": "http",
      "url": "https://agentfeed.bigfloppy.net/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "agentfeed": {
      "serverUrl": "https://agentfeed.bigfloppy.net/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "agentfeed": {
      "type": "http",
      "url": "https://agentfeed.bigfloppy.net/mcp"
    }
  }
}
```

## Tools

- `fetch_feed`: RSS/Atom feed to JSON, given a url
- `fetch_article`: Page to clean text, given a url

## FAQ

### Do I need an API key?

Not for the free tier, which allows 3 URLs a day per IP; a free trial key gives 50 requests a day.

### What does a paid key cost?

$5 per 100,000 requests, valid for one year, with no rate limit.

### How do I add it to Claude Code?

Run claude mcp add --transport http agentfeed https://agentfeed.bigfloppy.net/mcp.

### What are the output limits?

Summaries are truncated to 500 characters and article text is capped at 20,000.

### Is AgentFeed free?

AgentFeed has a free plan, with paid plans for more usage or features.

### How do I add AgentFeed to Claude Code?

Run this command in your terminal: claude mcp add --transport http agentfeed https://agentfeed.bigfloppy.net/mcp

### What are the best alternatives to AgentFeed?

The closest alternatives to AgentFeed are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and AI-Powered directory.

## Alternatives

- [Scrapling MCP Server](https://ai-powered.com/mcp/scrapling-mcp-server): Scrapling MCP Server is an open-source MCP server for web search and scraping.
- [Firecrawl MCP Server](https://ai-powered.com/mcp/firecrawl-mcp-server): Firecrawl MCP Server is a freemium MCP server for web search and scraping.
- [SearXNG Search](https://ai-powered.com/mcp/searxng-search): SearXNG Search is an open-source MCP server for web search and scraping.
- [NeuralVerge](https://ai-powered.com/mcp/neuralverge): NeuralVerge is an MCP server for web search and scraping.
- [AI-Powered directory](https://ai-powered.com/mcp/ai-powered-directory): AI-Powered directory is a free MCP server for developer tools.
- [Shopify MCP Server (any store)](https://ai-powered.com/mcp/shopify-mcp-server-any-store): Shopify MCP Server (any store) is a paid MCP server for e-commerce.
- [Chanroll: YouTube Channel Video Scraper (Official API)](https://ai-powered.com/mcp/chanroll-youtube-channel-video-scraper-official-api): Chanroll: YouTube Channel Video Scraper (Official API) is a paid MCP server for design and media.
- [Vidvett: YouTube Video Details Scraper (Official API)](https://ai-powered.com/mcp/vidvett-youtube-video-details-scraper-official-api): Vidvett: YouTube Video Details Scraper (Official API) is a paid MCP server for design and media.

---
Source: https://ai-powered.com/mcp/agentfeed-3
