@pipeworx/newswire-com

Live press releases from Newswire.com's public newsroom RSS feed — headline, publish time and sub-headline excerpt, newest first, for the 50 most recent releases. Newswire.com is an Issuer Direct wire, sibling to ACCESS Newswire, and carries a large share of the same releases.

Part of Pipeworx — an MCP gateway connecting AI agents to 1867+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

• newswire_com_latest_releases(since_hours?, limit?) — the current rolling window of releases, newest first (up to 50). newest_item_at tells a caller whether the feed is quiet or stalled.

• newswire_com_search_releases(query, limit?) — keyword/company match over headline and excerpt, within the current window only.

• newswire_com_get_release(url) — one specific release, matched by the URL a prior call returned. Fails clearly (not silently empty) if the release has scrolled out of the current window.

Related MCP server: businesswire

Auth

Keyless. No account, no clickthrough terms. newswire.com/robots.txt disallows only the per-tag feeds and asks for Crawl-delay: 5; the gateway's per-call result cache keeps polling well below that.

Data sources

• Newswire — the newsroom "Press Releases" channel. Measured 2026-09-22: 50 items spanning roughly a day.

Every call re-fetches this same rolling 50-item window live — it is not an archive. search_releases only ever searches what is currently in the window and get_release can miss something that has already fallen out of it (the tool says so explicitly rather than returning an empty result).

This feed carries no issuer field — the company name lives only in the headline or sub-headline — so issuer is null on every row rather than a guess parsed out of the headline.

The /feeds index page lists ~650 per-beat feeds (/newsroom/rss/beat/<slug>) and two "custom" feeds; every beat probed returned a bare nginx 404 and both custom feeds return HTTP 410 Gone (2026-09-22), so this pack does not enumerate them.

Relationship to ACCESS Newswire

ACCESS Newswire (formerly ACCESSWIRE) serves every feed path (/users/rss, /rss, /rss.xml, its sitemap index) and every article page behind a Cloudflare managed challenge (HTTP 403, cf-mitigated: challenge); its only open feeds, /feed/rss2 and /feed/atom, are its corporate blog, not the wire. Measured 2026-09-22: 12 of the 20 releases on ACCESS Newswire's newsroom landing page appeared verbatim in this feed. This pack is therefore the closest keyless, machine-readable surface to that wire — partial, not a mirror (fleet #2286).

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/newswire-com/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, 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 1867+ 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/newswire_com_latest_releases \
  -H 'Content-Type: application/json' \
  -d '{}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/newswire_com_latest_releases. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Run it from npm

@pipeworx/mcp-newswire-com is a local stdio bridge to the Pipeworx gateway: your MCP client starts it with npx, and it forwards every call to the same https://gateway.pipeworx.io/newswire-com/mcp endpoint shown above. It needs network access; there is no offline mode.

{
  "mcpServers": {
    "newswire-com": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-newswire-com"]
    }
  }
}

Without a key it calls anonymously, capped at 50 calls a day. A free account raises that to 200 a day: get a key at https://pipeworx.io/signup and add "env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry. The key is sent as a Bearer token, the same way a hosted connection sends it, so calls are metered and billed exactly as they are there.

It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to also list ask_pipeworx and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check your Node version's documentation.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Newswire Com data" })

The gateway picks the right tool and fills the arguments automatically.

More

• Docs and guides

• pipeworx.io

License

MIT