Travel Feeds logo

Travel Feeds

Read curated travel feeds or normalize RSS, Atom, and RDF feeds through MCP.

Install Travel 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": {
    "travel-feeds": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-travel-feeds"
      ]
    }
  }
}

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

We couldn’t confirm it starts correctly

The install command started, but didn't respond the way we expected when we tried to talk to it.

npx -y @pipeworx/mcp-travel-feeds

initialize succeeded but no response to tools/list.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 5d ago.

Overview

Travel Feeds MCP server lets agents discover curated travel feeds, read normalized feed items, and fetch arbitrary RSS, Atom, or RDF feeds by URL. It exposes three MCP tools through a hosted Pipeworx endpoint or a local stdio package. Use it when an agent needs current travel content with consistent fields such as title, link, publication date, and summary. Feed retrieval can fall back to a proxy when a source blocks direct access.

Use cases

  • Discover curated travel news sources by category or keyword
  • Read normalized entries from a selected travel feed
  • Fetch and standardize an RSS, Atom, or RDF feed
  • Filter feed items by a topic keyword
  • Expose travel feed retrieval to an MCP-compatible agent

Key features

  • Curated travel feed discovery
  • RSS, Atom, and RDF feed fetching
  • Normalized feed item fields
  • Category and keyword filtering
  • Direct-fetch and proxy fallback
  • Hosted HTTP and local stdio modes

Tools3

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

Self-reported~125 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 3d ago

Recent health check succeeded.

4/4 checks healthy over the last 44d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 2d ago via OSV.dev · @pipeworx/mcp-travel-feeds (npm)

Adoption & maintenance

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

npm downloads491Package downloads in the last 30 days.
Last commit1mo agoMost recent push to the default branch.
Install checkInconclusiveStarted but did not complete the MCP handshake in our test.
Tools exposed3Callable tools this server registers over MCP.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How Travel Feeds works

What Travel Feeds MCP server does

The Travel Feeds MCP server gives an MCP-compatible agent access to travel-related feed data. It supports two ways to find content: browse a curated catalog, or provide a feed URL directly. Returned entries are normalized so consuming applications can work with consistent fields instead of handling each feed format separately.

The curated catalog includes feed IDs, titles, categories, and source URLs. Agents can filter that catalog by the travel category or by a keyword. After selecting a feed ID, they can retrieve its items and optionally filter those items by keyword.

How it works

The server exposes three tools:

  • list_feeds returns available curated feeds and accepts optional category or keyword filters.
  • read_feed reads a curated feed selected by its ID and returns normalized items containing a title, link, publication date, and summary. A keyword filter is available for the items.
  • fetch_feed accepts a URL and fetches an RSS, Atom, or RDF feed, then converts its entries into the normalized format.

For direct retrieval, the Travel Feeds MCP server first attempts to fetch the source and can use a proxy fallback if the source blocks the gateway. The documented workflow is to use list_feeds for curated sources, then pass a selected ID to read_feed.

Setup and configuration

A hosted MCP connection is available at https://gateway.pipeworx.io/travel-feeds/mcp. The README provides configuration examples for Claude Desktop, Cursor, and Windsurf. The same gateway also has a full endpoint at https://gateway.pipeworx.io/mcp; the scoped endpoint lists this pack's tools directly, while both endpoints can reach the broader gateway through its shared routing tools.

The package can also run locally without a Pipeworx account or gateway round trip. Configure an MCP client to run npx -y @pipeworx/mcp-travel-feeds, or execute that command directly. The local process communicates over stdin and stdout and exposes only the travel-feed tools.

No environment variables are documented as required. The hosted HTTP tool API can also be called without an MCP client using POST requests to the gateway's tool endpoint.

Tools and capabilities

Use list_feeds when the agent needs to discover available curated sources before reading one. Use read_feed when the source is already identified by a catalog ID and the result should be limited to matching items. Use fetch_feed for a feed URL that is not part of the curated catalog or when an application needs to process its own RSS, Atom, or RDF source.

Each normalized item includes title, link, published, and summary. This makes the output suitable for tasks such as finding recent travel articles, filtering feed entries by a subject keyword, or presenting several sources in a common structure.

Limitations and notes

The Travel Feeds MCP server is focused on feed discovery and retrieval.

A scoped hosted connection includes shared Pipeworx meta-tools in addition to the three pack tools, so its tools/list response contains more tools than the local package. The exact hosted scope can change and is stated by the connection's initialize response. The local stdio mode does not include those shared meta-tools or cross-catalog routing.

Reviews

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

Frequently Asked Questions about Travel Feeds

Travel Feeds is an MCP server that connects AI agents to curated travel feeds and arbitrary RSS, Atom, or RDF sources. Its main tools are list_feeds for discovery, read_feed for normalized items from curated feeds, and fetch_feed for retrieving and normalizing a feed by URL.

Run it locally with `npx -y @pipeworx/mcp-travel-feeds` and configure your MCP client to use that command. You can instead connect to the hosted endpoint at `https://gateway.pipeworx.io/travel-feeds/mcp`; the local option does not require a Pipeworx account.

Configure Cursor with the hosted MCP URL, or use the documented local stdio command with an MCP configuration that supports command-based servers.

Yes, `fetch_feed` accepts an RSS, Atom, or RDF feed URL and normalizes its entries. Direct fetching can fall back to a proxy when the source blocks the gateway, while curated sources can be discovered first with `list_feeds`.

Normalized feed items include a title, link, publication date, and summary. `list_feeds` returns feed IDs, titles, categories, and sources, while `read_feed` and `fetch_feed` return feed entries.

Related MCP servers

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 PreviewTravel Feeds AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/travel-feeds?style=directory)](https://allmcps.com/mcp/travel-feeds)
HTML Embed
<a href="https://allmcps.com/mcp/travel-feeds"><img src="https://allmcps.com/api/badge/travel-feeds?style=directory" alt="Travel Feeds on AllMCPs" /></a>