Récupère un article par son identifiant ELI (European Legislation Identifier).
AI agents call legifrance_article_par_eli to retrieve information from Mpc Legifrance without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves ('récupère') a legal article by its ELI identifier. This is a pure read/fetch operation with no side effects, no data modification, and no destructive capabilities. The blast radius if misused is minimal — at most, an AI agent could retrieve unintended legal texts.
From the tool's definition Récupère un article par son identifiant ELI (European Legislation Identifier)
Attacks that exploit this kind of access
Récupère un article par son identifiant ELI (European Legislation Identifier). It is categorised as a Read tool in the Mpc Legifrance MCP Server, which means it retrieves data without modifying state.
Register the Mpc Legifrance MCP server in PolicyLayer and add a rule for legifrance_article_par_eli: 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 Mpc Legifrance. Nothing to install.
legifrance_article_par_eli 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 legifrance_article_par_eli 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 legifrance_article_par_eli. 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.
legifrance_article_par_eli is provided by the Mpc Legifrance MCP server (ktulu-analog/mcp-legifrance). 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 →