Query the Géoportail de l
AI agents call ign_get_gpu_urbanisme to retrieve information from IGN API Carto MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a geographic data retrieval tool that queries urban planning (urbanisme) zones from IGN's Géoportail. Like its siblings, it retrieves and returns geographic information without modifying, deleting, or executing operations. No side effects or state changes occur. The blast radius of misuse is limited to exposure of publicly-available French geographic data.
From the tool's definition Tool name 'ign_get_gpu_urbanisme' uses 'get' verb indicating a read operation. Description is incomplete ('Query the Géoportail de l') but 'get' and 'query' are standard retrieval patterns.
Attacks that exploit this kind of access
Query the Géoportail de l. It is categorised as a Read tool in the IGN API Carto MCP Server MCP Server, which means it retrieves data without modifying state.
Register the IGN API Carto MCP Server MCP server in PolicyLayer and add a rule for ign_get_gpu_urbanisme: 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 IGN API Carto MCP Server. Nothing to install.
ign_get_gpu_urbanisme 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 ign_get_gpu_urbanisme 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 ign_get_gpu_urbanisme. 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.
ign_get_gpu_urbanisme is provided by the IGN API Carto MCP Server MCP server (julienkalamon/ign-apicarto-mcp-server). 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 →