Prnewswire MCP server

@pipeworx/prnewswire

Live press releases from PR Newswire's site-wide RSS feed — headline, issuer, industry tags, publish time and excerpt, newest first.

Part of Pipeworx — an MCP gateway connecting AI agents to 1679+ live data sources.

Tools

window of releases, newest first. newestitemat tells a caller whether the feed is quiet or stalled.

• prnewswirelatestreleases(since_hours?, limit?) — the current rolling

headline, issuer, excerpt and industry tags, within the current window only.

• prnewswiresearchreleases(query, limit?) — keyword/company match over

prior call returned. Fails clearly (not silently empty) if the release has scrolled out of the current window.

• prnewswiregetrelease(url) — one specific release, matched by the URL a

Auth

Keyless. No account, no clickthrough terms.

Data sources

"All News Releases" feed. Its own description spans politics/government, business, technology, religion, sports/entertainment, science/nature and health/lifestyle, in English or other languages. It holds roughly the ~20 most recent releases site-wide — typically under two hours of volume — and every call re-fetches this same rolling window live. It is not an archive: searchreleases only ever searches what is currently in the window, and getrelease can miss a release that has already scrolled off.

• — PR Newswire's

The issuer name is pulled from , not from — that tag names PR Newswire itself on every item, not the issuer, so treating it as a byline would mislabel every release as being "by PRNewswire".

Cloudflare bot-management quirk, worth knowing if you extend this pack: the feed URL intermittently 301-redirects to a trailing-slash variant that itself 404s — roughly 1 in 3 fresh requests, measured live 2026-09-21 (8-request sample: 3/8). It is a cookie-issuing challenge redirect, not a real outage; the next fresh request typically succeeds. This pack retries up to 3 attempts before reporting the wire down.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "prnewswire": {
      "url": "https://gateway.pipeworx.io/prnewswire/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/prnewswire/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — askpipeworx, discovertools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1679+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/prnewswire_latest_releases \
  -H 'Content-Type: application/json' \
  -d '{}'

Shortened. The full README is on GitHub.