Skip to main content
Glama
Sirenic MCP server

Sirenic MCP server

Official

Search French associations by name

search_french_associations
Read-only

Identify French associations by name in the RNA registry, filter by postal code, department, or status, and return up to 20 matches with confidence scores and RNA numbers.

Instructions

Use FIRST whenever a French association (loi 1901, nonprofit, charity, club) is mentioned by NAME without an identifier. Searches the Répertoire national des associations (RNA) by normalised title prefix first, then by trigram similarity for similar titles (each result says which in correspondance), with optional postal-code, department and position filters applied before the cut. Returns up to 20 matches with score_confiance (0-1) and the RNA number to pass to get_french_association_profile or get_french_association_notices; siren when Sirene confirms it. total_results counts, before the cut, every title that passes the query and the filters in the pool of each stage run, a typed RNA number included (served and counted even outside the filters); it is a lower bound (listes_bornees.resultats) when a stage finds more than 3000 filtered titles or is abandoned. Associations with AND without a SIREN; the legacy file (no declaration since 2009) is flagged fichier_source: import. Paid via x402 ($0.002 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": {
      "q": "<q>"
    },
    "name": "search_french_associations"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesAssociation title, or an RNA number (resolved directly). Unsupported characters are stripped, not rejected.
positionNoPosition filter; default all
code_postalNoPostal code or prefix (2-5 digits) of the registered office
departementNoRegistered-office departement, by postal code: 01-19, 21-95, 971-978; 2A, 2B, 984, 986-989 refused for now (400 departement_non_servi, not charged); code_postal wins over a served departement; any other departement is refused, even with code_postal

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

A4.6/5.0
Behavior5/5

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

Far exceeds the readOnlyHint/openWorldHint annotations: it discloses the two-stage matching strategy (normalised title prefix, then trigram similarity, with correspondance telling you which), that filters are applied before the cut, a 20-result cap, the score_confiance range, the siren-conditional field, the fichier_source: import legacy flag, and the 3000-title lower-bound caveat on total_results. It also discloses the x402 payment ($0.002 USDC or EURC) and a citation obligation.

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 routing instruction is correctly front-loaded, but the body is a dense run-on of semicolon-joined clauses covering matching stages, result fields, total_results accounting and pricing in one breath. Some of it (total_results semantics, score_confiance range) overlaps an existing output schema and could be trimmed or deferred there, which would make the key selection guidance easier to scan.

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?

Covers everything an agent needs before calling: matching behaviour, filter precedence, result cardinality and fields, the lower-bound caveat on counts, source-file caveat, cost and citation requirement. An output schema exists, yet the extra return details do not leave any behavioural gap.

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

Parameters5/5

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

Although schema coverage is 100%, the description adds meaning the schema does not: that q also resolves a typed RNA number (served and counted even outside the filters), that characters are normalised rather than rejected, and that code_postal wins over departement when both are supplied.

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?

States a specific verb and resource (search the RNA by association title) and scopes it to French loi 1901 associations, nonprofits, charities and clubs named without an identifier. It is immediately distinguishable from get_french_association_profile and get_french_association_notices, which it names as downstream consumers of the returned RNA number.

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?

Gives an explicit routing rule — 'Use FIRST whenever a French association ... is mentioned by NAME without an identifier' — and points to the follow-up tools for profile and notices. It stops short of naming the alternative for the opposite case (e.g. companies, where search_french_companies or search_european_companies would apply), so the exclusion side is only implied.

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