Skip to main content
Glama
Sirenic MCP server

Sirenic MCP server

Official

UK company public procurement (FTS, Contracts Finder)

get_uk_company_public_procurement
Read-only

Retrieve a UK company's public procurement records by company number, including contracts won, notices issued, values, dates, statuses, and official notice links from UK feeds.

Instructions

Public-procurement record of a UK company from Find a Tender (above-threshold notices since 2021) and Contracts Finder (below-threshold since 2023), Cabinet Office OCDS feeds under OGL v3: contracts WON matched by company number (attributions: buyer, subject, contract value in GBP, award / signature dates, contract period, status, official notice link, source fts | cf) and notices ISSUED as a buyer (avis_emis), newest first, 100 each at most with tronque_*, totals (nombre_attributions, valeur_totale_gbp, nombre_avis_emis) and stock per feed. Only about half of suppliers carry a company number and natural persons never do: aucune_attribution: true is a NON-conclusive absence; aucun_marche: true means the company was confirmed at Companies House with nothing matched. Facts only, no score. A company with a current name under objection (GDPR art. 21) returns the same 404 as an unknown number, not billed; a supplier's published name, a buyer's name or a title under objection is served null and counted in ecartes.opposition (item kept, only its block partial in provenance); a title naming a person (title of address and name, T/A, sole trader) is null, counted in ecartes.personne_physique. 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": {
      "company_number": "<company_number>"
    },
    "name": "get_uk_company_public_procurement"
  }
}

Input Schema

NameRequiredDescriptionDefault
company_numberYes8-character UK company number, leading zeros included (e.g. 10868035, SC540982)

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

A4.5/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial behavioral context beyond them — per-feed caps of 100 with `tronque_*` truncation flags, cost and payment mechanics ($0.02 USDC/EURC via x402), and a 404 that returns for a name under GDPR art. 21 objection the same way as an unknown number and is not billed. It further discloses partial-redaction behavior (null names counted in `ecartes.opposition`, person-named titles nulled and counted in `ecartes.personne_physique`) and the requirement to cite `citation` verbatim.

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 scoping and caveats are front-loaded and nearly every clause carries information, but the first sentence is a single sprawling enumeration of output fields that largely duplicates the existing output schema. The result is a dense block with behavioral caveats, pricing, and redaction rules stacked in sequence rather than separated, making it harder to scan than its content warrants.

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

Completeness5/5

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

For a paid, open-world lookup with one input, everything an agent needs is present: source coverage windows, result caps and truncation flags, absence semantics, objection/redaction handling, billing, and the citation obligation. The verbose field enumeration is redundant given the output schema, but nothing material is missing.

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% for the single `company_number` parameter, so the baseline is 3. The description nonetheless adds meaning the schema cannot: matching is performed on company number, and that key is only populated for roughly half of suppliers and never for natural persons, which tells the agent how to interpret empty results relative to the input.

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 pair (public-procurement record of a UK company) and scopes it to two named sources with their coverage windows (FTS above-threshold since 2021, Contracts Finder below-threshold since 2023). It distinguishes the two record types it returns — contracts WON via `attributions` and notices ISSUED as a buyer via `avis_emis` — which an agent can tell apart from sibling registry/accounts/insolvency tools without opening a schema.

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

Usage Guidelines4/5

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

It gives clear interpretive conditions for use: `aucune_attribution: true` is explicitly NON-conclusive because only about half of suppliers carry a company number and natural persons never do, while `aucun_marche: true` means confirmed at Companies House with nothing matched. What it does not do is explicitly route against alternatives (e.g. national procurement tools for other jurisdictions or the competitor tool), so usage context is clear but exclusions are absent.

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