Validates a French SIRET (14-digit company establishment number) using the official Luhn algorithm. The first 9 digits are the SIREN (company identifier) and the last 5 identify the specific establishment. Returns { valid: boolean, siren: string, establishment: string, siret: string } or { valid:...
AI agents call validate_siret to retrieve information from Mcp Europe Business without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure validation/lookup tool that checks the format and authenticity of a French SIRET number using the Luhn algorithm. It retrieves and returns structured data about the input (siren, establishment identifiers) but does not create, modify, delete, or execute any operations.
From the tool's definition Tool description states it 'Validates a French SIRET' and 'Returns { valid: boolean, siren: string, establishment: string, siret: string }'.
Attacks that exploit this kind of access
Validates a French SIRET (14-digit company establishment number) using the official Luhn algorithm. The first 9 digits are the SIREN (company identifier) and the last 5 identify the specific establishment. Returns { valid: boolean, siren: string, establishment: string, siret: string } or { valid: false, reason: string }. Handles the La Poste special case automatically (SIREN 356000000 uses sum-modulo-5 instead of Luhn). Use when processing French B2B invoices, supplier validation, or any French business compliance workflow involving establishment-level identification. It is categorised as a Read tool in the Mcp Europe Business MCP Server, which means it retrieves data without modifying state.
Register the Mcp Europe Business MCP server in PolicyLayer and add a rule for validate_siret: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Europe Business. Nothing to install.
validate_siret is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the validate_siret rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for validate_siret. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
validate_siret is provided by the Mcp Europe Business MCP server (josemvelez78/mcp-europe-business). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →