Log inSubmit server
Security Feeds logo

Security Feeds

Browse curated cybersecurity feeds or normalize RSS, Atom, and RDF sources for agent workflows.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Security Feeds

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "security-feeds": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-security-feeds"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 3 tools correctly (4d ago).

Overview

Security Feeds MCP server lets AI clients discover curated cybersecurity feeds, read normalized entries, and process arbitrary RSS, Atom, or RDF URLs. It exposes three focused tools: list_feeds, read_feed, and fetch_feed, with keyword filtering available during discovery and reading. The hosted endpoint runs through the Pipeworx gateway, while a standalone npm package provides local stdio access. Reach for it when an agent needs current feed content rather than direct access to a security data platform.

Use cases

  • Discover curated cybersecurity sources by category or keyword
  • Read normalized security feed items for agent analysis
  • Fetch an RSS, Atom, or RDF URL supplied at runtime
  • Filter feed entries by a keyword
  • Run the feed tools locally over MCP stdio

Key features

  • Curated cybersecurity feed discovery
  • Normalized RSS, Atom, and RDF entries
  • Keyword filtering for feeds and items
  • Proxy fallback for blocked feed sources
  • Hosted gateway and local stdio modes

Tools3

What Security Feeds lets your agent do. Expand a tool for its parameters.

Verified live~398 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

7/7 checks healthy over the last 55d

What it can do

From the 3 tools this server returned when we ran it; 3 declare their own safety hints.

Makes network requests · 3Read-only tools · 3
Network at startup4 connections
Files written at startupNone
Install scriptsNone
npm provenanceSigned build
Package age132 days
Maintainers1

Observed 2026-11-04 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 13d ago via OSV.dev · @pipeworx/mcp-security-feeds (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads278Package downloads in the last 30 days.
Last commit3d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed3Callable tools this server registers over MCP.

How Security Feeds works

What Security Feeds MCP server does

Security Feeds MCP server gives MCP-compatible agents a small interface for working with cybersecurity news and feed data. It provides a catalog of curated feeds, lets an agent select a feed from that catalog, and can fetch a feed directly when the required source is not part of the curated collection.

The returned feed entries are normalized into fields including title, link, published date, and summary. This makes results easier for an agent to compare, filter, or present consistently across different feed formats. Supported source formats are RSS, Atom, and RDF.

How it works

An agent can start with list_feeds, which returns feed identifiers, titles, categories, and source details. The optional category or keyword filters help narrow the catalog. After selecting an identifier, the agent can call read_feed to retrieve entries from that curated source and optionally filter those entries by keyword.

For a source outside the catalog, fetch_feed accepts a feed URL and normalizes the response. The fetch operation first attempts to access the source directly and can fall back to a proxy when the source blocks the gateway. This makes the Security Feeds MCP server suitable for workflows that combine known sources with a specific feed supplied at runtime.

Setup and configuration

The hosted MCP endpoint is available at:

https://gateway.pipeworx.io/security-feeds/mcp

Add that URL to an MCP client as a remote server. The gateway also exposes a full Pipeworx endpoint at https://gateway.pipeworx.io/mcp; both endpoints reach the same gateway and data sources, but the scoped endpoint lists this pack's tools directly. The scoped gateway connection also includes shared Pipeworx meta-tools, including routing and discovery tools.

For local execution, run the npm package with npx -y @pipeworx/mcp-security-feeds and configure the command as an MCP stdio server. Local mode does not require a Pipeworx account or gateway round trip and exposes only this pack's three tools.

Tools and capabilities

  • list_feeds: Enumerates curated cybersecurity feeds and supports category or keyword filtering.
  • read_feed: Reads a curated feed by its identifier and returns normalized entries, with optional item keyword filtering.
  • fetch_feed: Retrieves and normalizes an RSS, Atom, or RDF feed from a supplied URL.
  • Proxy fallback: Allows fetch_feed to retry through a proxy when a source blocks the gateway.
  • Plain-language routing: Gateway users can use ask_pipeworx to ask questions instead of invoking a pack tool directly.

Limitations and notes

The curated feed list is the intended starting point for known sources, while arbitrary URLs must be supplied to fetch_feed. The gateway endpoint includes shared meta-tools in addition to the three pack-specific tools, so its tool listing is larger than the standalone server's listing. The exact gateway scope is reported during MCP initialization.

Feed availability and the contents of normalized entries depend on the upstream source.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Security Feeds

Security Feeds is an MCP server that connects AI clients to curated cybersecurity feeds and arbitrary RSS, Atom, and RDF URLs. Its main tools are list_feeds for discovery, read_feed for normalized curated items, and fetch_feed for fetching and normalizing feeds from supplied URLs, including proxy fallback when needed.

Run `npx -y @pipeworx/mcp-security-feeds` and configure it as a local MCP stdio server. Alternatively, add the hosted endpoint `https://gateway.pipeworx.io/security-feeds/mcp` to a remote-capable MCP client.

Call `fetch_feed` with the feed URL. The tool accepts RSS, Atom, and RDF sources, normalizes their entries, and can fall back to a proxy if the source blocks the gateway.

Call `list_feeds`, optionally providing a category or keyword filter. Use an ID from the results with `read_feed` to retrieve normalized items from the selected source.

Yes. Configure Cursor with the hosted MCP URL or the local `npx` stdio command. The README specifically lists Cursor among supported MCP clients.

Related MCP servers

All in Security All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewSecurity Feeds AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/security-feeds?style=directory)](https://allmcps.com/mcp/security-feeds)
HTML Embed
<a href="https://allmcps.com/mcp/security-feeds"><img src="https://allmcps.com/api/badge/security-feeds?style=directory" alt="Security Feeds on AllMCPs" /></a>