Vérifie la validité d
AI agents call verifier_siret to retrieve information from French Admin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or validates information about a business identifier (SIRET) without creating, modifying, or deleting data. It is a read-only operation that queries existing administrative data to verify authenticity. The low severity reflects minimal blast radius—an AI agent misusing this would at worst validate incorrect business identities, with no irreversible consequences.
From the tool's definition Tool name 'verifier_siret' and description indicate verification/validation of a SIRET number (French business identifier). The action is to check validity, which is a lookup/query operation with no data modification or side effects.
Attacks that exploit this kind of access
Vérifie la validité d. It is categorised as a Read tool in the French Admin MCP Server, which means it retrieves data without modifying state.
Register the French Admin MCP server in PolicyLayer and add a rule for verifier_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 French Admin. Nothing to install.
verifier_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 verifier_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 verifier_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.
verifier_siret is provided by the French Admin MCP server (mcp-tools-lab/french-admin-mcp). 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 →