@pipeworx/poland-tenders

Polish government procurement notices (zamówienia publiczne) — recent, keyword/CPV, and buyer-filtered search over the national BZP bulletin.

Part of Pipeworx — an MCP gateway connecting AI agents to 1807+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

• pl_tender_recent(days?, limit?) — the most recently published Polish contract notices.

• pl_tender_search(query, date_from?, date_to?, limit?) — keyword/CPV search over notices in a publish-date window.

• pl_tender_by_buyer(buyer, date_from?, date_to?, limit?) — notices published by a given contracting authority.

Related MCP server: Atlas Przetargów

Auth

Keyless. The notice-read endpoint is the public surface of the platform and needs no registration or integration procedure.

Data sources

• Urząd Zamówień Publicznych (Poland Public Procurement Office), Biuletyn Zamówień Publicznych notice bulletin, served via the official e-Zamówienia platform.

Notes for the next person

The upstream notice API has two quirks that shape every tool here:

1. PageNumber is accepted but silently ignored — asking for page 1, 2, or 3 of the same date-range query returns byte-identical results. There is no working server-side pagination, verified live.

2. Within one date range the API returns notices OLDEST-FIRST, hard-capped at PageSize<=500. Daily volume runs ~450-500 notices, so a multi-day window risks the 500 cap silently truncating away the NEWEST notices (at the end of ascending order) rather than the oldest — the opposite of what a caller would expect from "the window got too big."

Because of both, every tool here fetches one calendar day per HTTP call (never a multi-day range in one request) and merges/sorts client-side — newest-day-first, so a per-call day cap drops the oldest days rather than hiding the newest ones. There is no server-side keyword/buyer/CPV filter either, so matching is done client-side over the fetched days.

Each raw notice embeds a large htmlBody field (the full rendered notice page, tens of KB) which is discarded during shaping and never returned to a caller.

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/poland-tenders/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 1807+ 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/pl_tender_recent \
  -H 'Content-Type: application/json' \
  -d '{"limit":5}'

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

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

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

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-poland-tenders

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

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 Poland Tenders data" })

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

More

• Docs and guides

• pipeworx.io

License

MIT