Skip to main content
Glama
Sirenic MCP server

Sirenic MCP server

Official

Create a company watch

create_surveillance_watch

Create a 30-, 90-, or 365-day watchlist to monitor French companies and directors daily, delivering signed webhook or email alerts for filings, status changes, sanctions, and public-office events.

Instructions

Company monitoring for France, for when the relationship OUTLASTS the check (customer, borrower, supplier, portfolio company): create a 30, 90 or 365-day watchlist over French companies and/or directors. A director target (dirigeant:Name) is a name only, namesakes included, reserved to identified Sirenic accounts: pass api_key, without x_payment, otherwise 401 compte_requis and nothing is charged. Sirenic checks every target DAILY (BODACC filings, status & officer changes, sanctions and AMF-blacklist matches, PSAN/SGP status, Seveso/ICPE changes, new French & EU procurement awards, and since 2026-09-24 commercial-court decisions newly linked to the company, event decision_tcom_rattachee; for directors: new/ended public offices, diffed only on a complete list, a name matching more companies than one page, a company removed by a GDPR objection, or a name matching one, being marked mandats_partiels (from creation when the list read then is already incomplete)) and delivers events via Ed25519-signed webhook and/or e-mail digest, always pollable with the returned bearer token, plus an expiry reminder 7 days ahead. An official source that cannot be read emits one surveillance_degradee per outage, then surveillance_retablie (source, ouverte_le, retablie_le) at the first check that reads it again. Event types and payloads: listes_fermees.type_evenement_surveillance of GET /v1/lecture (free). An API key (api_key) pays it from its account credits instead of x402. A watchlist created with a key is listed in that account's client area (GET /compte/surveillances with the key), where it can be stopped; one paid via x402 can be linked there by its token. renouvellement=auto (paid with an account key only) opts in to automatic renewal on the account credits at each expiry, same duration, never above the amount stated in renouvellement_automatique (stop it in the client area). Paid via x402, per target AND per duration: $0.05 for 30 days, $0.135 for 90 days, $0.50 for 365 days (amount = that unit price × number of targets, so up to $50.00 for 100 targets over a year). No pro-rata refund. A full-size request quotes up to $50.00, above the $1.00 single-payment cap that x402 clients apply BY DEFAULT since @x402/core 2.23 (spendControls): raise spendControls.maxAmountPerPayment, or set spendControls: false, before signing; otherwise your own client rejects the quote without ever calling us. 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": {
      "cibles": "<cibles>"
    },
    "name": "create_surveillance_watch"
  }
}

Input Schema

NameRequiredDescriptionDefault
dureeNoWatch duration in days (default 30). Sets the unit price per target: 30 = $0.05, 90 = $0.135 (-10%), 365 = $0.50 (-17.8% vs the monthly rate).
emailNoOptional e-mail address for digests
ciblesYes1-100 comma-separated targets: 9-digit SIRENs, RNA numbers (W + 9, associations: JOAFE notices) and/or dirigeant:Name entries (identified accounts only)
webhookNoOptional public https URL for signed event batches
renouvellementNoOptional: auto renews this watchlist from the account credits at each expiry, same duration, never above the amount stated in renouvellement_automatique; paid with an account key only, refused before any charge otherwise

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?

Far exceeds the annotations: it discloses auth outcomes (401 compte_requis, nothing charged), the daily check cadence and covered sources, delivery mechanics (Ed25519-signed webhook, e-mail digest, pollable bearer token), degradation events (surveillance_degradee / surveillance_retablie), expiry reminders, and the 'no pro-rata refund' rule. The x402 spend-cap warning ($1.00 default vs a $50.00 quote, spendControls.maxAmountPerPayment) is exactly the kind of client-side failure an agent could not infer from structured fields. Nothing here conflicts with readOnlyHint=false, idempotentHint=false, or destructiveHint=false.

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 core purpose and the pricing/spend-cap warning are front-loaded and every major clause carries genuine information. However, it is delivered as one very long paragraph with parentheses nested three and four levels deep (the mandats_partiels aside is effectively unparseable), and the enumerated source list (PSAN/SGP, Seveso/ICPE) is detail that helps monitoring semantics but burdens tool selection.

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 non-idempotent, billed, open-world creation tool this is essentially complete: auth, payment rails, renewal, delivery, failure modes, and cost ceilings are all covered, and an output schema exists so return values needn't be described. The instruction to cite `citation` verbatim even closes the reporting loop.

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%, so the baseline is 3; the description earns more by adding pricing derivation (unit price × target count, up to $50.00), the account-key restriction on renouvellement=auto and its refusal before any charge, and the account-linking paths for key-paid vs x402-paid watchlists. The dirigeant:Name target format and its namesake/GDPR caveats add real meaning beyond the 'cibles' schema text, though the reference to renouvellement_automatique is left dangling outside the schema properties.

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 up front: create a 30/90/365-day watchlist over French companies and/or directors, with daily monitoring. It is immediately distinguishable from the get/renew/stop_surveillance_watch siblings by the verb, and the opening framing ('when the relationship OUTLASTS the check') tells the agent this is ongoing monitoring rather than a one-off lookup.

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 a clear selection context (customer, borrower, supplier, portfolio company relationships that outlast a single check) and prerequisite conditions: director targets require an identified Sirenic account, renouvellement=auto requires an account key. It never explicitly names an alternative tool for the one-off case or points to stop_surveillance_watch for cancellation, so the routing guidance is contextual rather than exhaustive.

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