Skip to main content
Glama
Sirenic MCP server

Sirenic MCP server

Official

Polish company public procurement (BZP)

get_polish_company_public_procurement
Read-only

Retrieves Polish public-procurement records for a company NIP, showing contracts won and notices issued from e-Zamówienia, with buyer, CPV, price, and outcome details.

Instructions

Public-procurement record of a Polish company from the Biuletyn Zamówień Publicznych (e-Zamówienia public API, UZP, CC0; national below-EU-threshold notices since 2021, daily updates): contracts WON matched by legal-person NIP (attributions, one per awarded part: buyer with NIP, subject, CPV, closed-list outcome, tenders received, awarded price and contract value in PLN as published, contract date, declared enterprise size) and notices ISSUED as a buyer (avis_emis); newest first, capped at 100 with tronque_*. Winners are served only when PROVEN legal persons (legal form in the name or KRS from the VAT white list): sole traders (37 % of winners) are never served (400 without charge), a NIP not yet classified answers 404 without charge (stock.gagnants_a_classer), and so does a source placeholder NIP (identifiant_bouche_trou); a published name without its own legal form is left out (gagnant.nom_publie null, counted in ecartes). A dubious published value (contract date out of bounds or after its notice, a winner name carrying an address) is served as published with a closed-list reserves[] on its line, counted in reserves_lignes. Partial coverage: zero never means “never won a contract”. Paid via x402 ($0.02 in USDC or EURC). When you report a result, cite its citation verbatim.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "nip": "<nip>"
    },
    "name": "get_polish_company_public_procurement"
  }
}

Input Schema

NameRequiredDescriptionDefault
nipYesPolish NIP (tax identifier): ten digits, separators and PL prefix tolerated, e.g. 7812034808

Output Schema

NameRequiredDescriptionDefault
hintNoHow to settle the quote, present when payment_required is true.
quoteNoThe signable x402 payment requirements when payment_required is true: {x402Version, accepts[]} where each entry carries scheme, network, amount, asset and payTo (USDC and EURC options at the same numeric amount). Sign one entry and call again with `x_payment`.
resultatNoThe endpoint's JSON response when payment_required is false. Paid responses carry `source`, `disclaimer` and an Ed25519 signature, and every paid JSON response carries a `provenance` array (all tools since 2026-09-06): one entry per block served, with the official register, licence, version, `empreinte_sha256` (full snapshots), `as_of` date and `precision_as_of` (what that date means), plus the common per-block envelope: `etat` in a closed list (servi, absence_mesuree, absence_non_conclusive, partiel, perime, indisponible, sans_objet), `motif` when unavailable, `age_jours` (only for publication or ingestion dates), `couverture` (complete / partielle / non_mesurable with its measure) and `confiance` in bands (faible / moyenne / forte, only where a measure grounds it, never averaged across blocks). Read the states before the numbers: an absence_non_conclusive, indisponible or partiel block is never « nothing to report »; only absence_mesuree asserts an absence. Register codes: GET /v1/provenance/registres ; states, closed lists and reading rules: GET /v1/lecture (both free). The PDF tools carry no JSON envelope (the PDF report prints it).
free_tierNoFree API key offer for this tool, present with a quote.
payment_requiredYesTrue when this response is an x402 payment quote instead of data: settle one of the quote's `accepts` options and call the tool again with `x_payment`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint and openWorldHint, so the description carries real weight and delivers: partial coverage caveat ('zero never means never won'), 400/404 responses without charge, 100-row cap with `tronque_*`, `reserves[]` handling of dubious values, and a $0.02 x402 payment. That is unusually rich behavioral disclosure beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, but the body is a single dense run-on packed with internal field names (`stock.gagnants_a_classer`, `identifiant_bouche_trou`, `ecartes`, `reserves_lignes`) and mixed French/Polish identifiers. Every fact is arguably relevant, but the lack of structure and sentence discipline hurts readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description needn't explain return shapes, and it covers coverage limits, gating rules, truncation, and cost well. The one remaining gap is operational: 'paid via x402' is stated but not elaborated, leaving the payment flow to the agent's own knowledge.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and documents the NIP format, so the baseline is 3. The description adds genuine meaning: the NIP is used to match legal persons, and winners are only served when proven legal persons (legal form in name or KRS from the VAT white list), which explains why a valid NIP can still yield 404.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb+resource: a Polish company's public-procurement record from the Biuletyn Zamówień Publicznych, covering both contracts WON (`attributions`) and notices ISSUED as buyer (`avis_emis`). It also scopes the source precisely (national below-EU-threshold notices since 2021), which cleanly separates it from the EU-level and other-country procurement siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the country/coverage framing (Polish, national below-threshold) rather than stated as explicit when-to-use vs. when-to-use-an-alternative guidance. It does give concrete outcome conditions (400 for sole traders, 404 for unclassified NIPs or placeholder NIPs) that tell an agent when a call will fail, but no explicit routing to `get_european_company_eu_procurement` for above-threshold work.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools