legifrance_historique_texte
AI agents call legifrance_historique_texte 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.
Based on the server context (French law API, read-only legislative data) and the tool name implying retrieval of text history, this is almost certainly a read operation. However, confidence is lowered significantly because the description is empty and uninformative, preventing definitive classification.
From the tool's definition Tool name contains 'historique' (history) and 'texte' (text), suggesting retrieval of historical versions of legal texts from the Légifrance API.
Attacks that exploit this kind of access
legifrance_historique_texte. 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_historique_texte: 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_historique_texte 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_historique_texte 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_historique_texte. 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_historique_texte 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 →