Skip to main content
Glama
Sirenic MCP server

Sirenic MCP server

Official

Search EU financial authorisations (ESMA, ECB, EIOPA)

search_eu_financial_authorisations
Read-only

Verify whether a financial firm is regulated in the EU by searching five official registers (ESMA, ECB, EIOPA) by name or LEI, returning status, authority, and dates.

Instructions

Search EU financial authorisations in five official registers by name or LEI: ESMA Registers (MiFID-regulated entities across all EU/EEA countries: status, home and host member states, competent authority, dates), the ECB list of supervised entities (supervision_bce: banking union, significant banks under direct ECB supervision and less significant ones under national authorities, group, remarks, monthly changes; absence is conclusive only for a LEI and never means unsupervised outside the banking union), the ESMA register of benchmark administrators (administrateurs_indices), the ESMA register of money market funds (fonds_monetaires: fund and manager LEI, type, domicile, authorisation status incl. Withdrawn, dates) and the EIOPA register of occupational pension institutions (iorp: national authority, registration dates incl. closed registrations, cross-border activity, managing entity; only 30% carry a LEI, so zero by LEI is never conclusive). A block listed in blocs_absents was not read: panne_amont (retry later), stock_perime or collecte_en_cours (local copy too old or never loaded: retrying does not help). Use to verify that a financial firm is actually regulated somewhere in the EU. Data freely available at the sources. An entry whose own name, trading name or manager (money market funds, IORPs) is under objection (GDPR art. 21) is neither served nor counted, with no ecartes field; nombre_total (top level or of a block) may be null, unknown, when an ESMA register's matches under such an objection cannot all be re-read, or their re-read failed (such a page is not cached: the next call reads the register again; GET /v1/lecture), and an item of supervision_bce.entites[].changements is null when it names a person who objected, counted in the entity's ecartes.opposition. An ESMA MiFID entry run by a natural person (a written natural-person mark such as e.K., v/ or sole trader, or a LEI that GLEIF calls a natural person) or in doubt (an ambiguous LEI legal form, or an investment firm with neither a LEI known to GLEIF nor a written legal-person form) is never served: it is left out and counted without identity in agrements_omis (personne_physique, forme_juridique_non_reconnue), and stays counted in nombre_total; when GLEIF cannot be read for the page, 503, not charged. Paid via x402 ($0.01 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_eu_financial_authorisations"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesEntity name or 20-character LEI. Unsupported characters are stripped, not rejected.
paysNoOptional ISO-3166 alpha-2 home-member-state filter, an EU/EEA state: AT, BE, BG, CY, CZ, DE, DK, EE, ES, FI, FR, GR, HR, HU, IE, IS, IT, LI, LT, LU, LV, MT, NL, NO, PL, PT, RO, SE, SI, SK; another code: 400, not charged.

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

A4.3/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint; the description layers on substantial behavioral detail the annotations cannot carry: paid access via x402 at $0.01, non-charging on 400/503, cache behavior on unreadable pages, GDPR art. 21 objection suppression and resulting null `nombre_total`, the `blocs_absents` failure taxonomy (panne_amont vs stock_perime/collecte_en_cours and which are worth retrying), and the `agrements_omis` natural-person exclusion rule. Nothing here contradicts readOnlyHint.

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 and nearly every clause carries real information for a genuinely complex tool, but the opening is a single ~150-word run-on sentence with deeply nested parentheticals, making it hard to parse. With an output schema present, some of the field-by-field explanation (nombre_total, ecartes, agrements_omis) could be trimmed or reorganized into shorter sentences.

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 five-register, pay-per-call, GDPR-sensitive tool this covers cost, error semantics, caching, result-interpretation caveats, and the citation requirement. Because an output schema exists, the description need not enumerate return values, and it stays appropriately at the level of behavior and caveats.

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?

Schema coverage is 100% and both parameters are fully described in the schema, including the LEI length and the ISO-3166 alpha-2 pattern with the 400-not-charged consequence. The description's 'by name or LEI' and its market-fragmentation talk add marginal framing but no syntax or format meaning beyond the schema, so the baseline 3 applies.

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?

Opens with a specific verb and resource ('Search EU financial authorisations in five official registers by name or LEI') and then enumerates each of the five registers with its distinguishing content (MiFID entities, ECB supervised entities, benchmark administrators, money market funds, IORPs). An agent can tell exactly what corpus this covers and what each register contributes, which is more than the title alone conveys.

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?

States a clear use case: 'Use to verify that a financial firm is actually regulated somewhere in the EU,' plus interpretive rules on when a negative result is conclusive (ECB absence conclusive only for a LEI; IORP zero-by-LEI never conclusive). It does not name any alternative tool or an explicit when-not, so it stops short of full routing guidance.

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