Skip to main content
Glama
Sirenic MCP server

Sirenic MCP server

Official

French public contracts won

get_french_company_public_procurement
Read-only

Retrieve French public procurement contracts and tenders won by a company from its 9-digit SIREN, including buyers, amounts, dates, lots, and framework-agreement details.

Instructions

Public procurement in France: government contracts and tenders won by a French company (official DECP data), with buyers, amounts, dates, lot number when the subject states one, joint-holder count, and how to READ the amount: modalitesExecution tells whether it is a firm price or an ENVELOPE (call-off orders, subsequent contracts, optional tranches; 43% of contracts), and declared subcontracting with its amount tells what the holder does not keep. An amount covers the whole awarded contract or LOT over its full duration, excl. VAT; on a framework agreement it is a MAXIMUM CEILING, not spend (the total is split into ceilings vs firm commitments). Also CCAG, price type, advance and its rate, EU/French content ratios, amendment rank and dates, and the platform that published the record. Totals come as TWO BOUNDS: nombre_marches/montant_total count every published row (upper bound), nombre_marches_dedoublonne/montant_total_dedoublonne count one row per (buyer, notification date, amount, CPV) key (lower bound), as the same award is often published twice (two platforms, two establishments of the holder, repeated row, amendment); each row carries publication.statut (closed list) and its linked rows, and identifiant_partage flags a buyer id reused for distinct purchases. Paid via x402 ($0.01 in USDC or EURC). Names are served for legal persons proven by their Sirene legal category only: a sole proprietorship, a group of natural persons or a category in doubt never has its name served and keeps its SIREN or SIRET, the omissions counted without identity in ecartes, over the entries the response serves (rule R1). A contract subject that names a person by a civility followed by a capital letter (M., Mme, Monsieur, Madame, Maître…) is served null, counted without identity in ecartes; the contract stays (rule R1). 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": {
      "siren": "<siren>"
    },
    "name": "get_french_company_public_procurement"
  }
}

Input Schema

NameRequiredDescriptionDefault
sirenYes9-digit SIREN

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

A3.8/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint; the description goes far beyond them. It discloses the cost and payment rail (x402, $0.01 in USDC or EURC), the redaction policy that withholds names for non-legal persons and for subjects naming a civility, how omissions are surfaced in `ecartes`, the meaning of the two result bounds (published rows vs deduplicated key), and a citation obligation on reporting.

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?

Most content is substantive (amount-as-ceiling semantics, deduplication bounds, redaction rules), but it arrives as a single dense run-on paragraph that mixes usage, data semantics, pricing, and citation policy without headings or prioritization. The agent must parse several sentences to extract the two rules that actually govern invocation and reporting.

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?

An output schema exists, so return structure need not be spelled out, and the description instead explains the interpretation traps (envelope vs firm price, ceiling vs spend, duplicate publications). It is nearly complete for a complex read tool, but says nothing about result volume, limits, or paging behavior.

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

Parameters3/5

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

There is a single parameter, `siren`, documented at 100% schema coverage as a 9-digit SIREN. The description adds no format, validation, or lookup-failure context beyond that, so the schema fully carries the burden and the baseline of 3 applies.

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

Purpose4/5

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

The description names a specific verb+resource combination: government contracts and tenders WON by a French company, sourced from official DECP data. The company-side scope distinguishes it implicitly from buyer-side siblings such as get_french_public_buyer_profile and from the other country-specific procurement tools, though it never names an alternative explicitly.

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 rather than stated: an agent can infer it should call this with a SIREN to retrieve that company's awarded contracts. There is no explicit when-to-use/when-not guidance and no routing to adjacent tools like find_expiring_french_public_contracts, get_eu_procurement_awards, or the non-French procurement siblings, so the agent must infer boundaries from names alone.

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