AI agents use add_popup to create or update resources in Leaflet — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Leaflet environment.
add_popup generates Leaflet popup code, which modifies map configuration by adding popup elements. This is Write-category: it creates/generates interactive map components reversibly. The blast radius is minimal since popups are UI enhancements with no side effects on underlying data, external systems, or financial operations.
From the tool's definition Tool generates code for 'creating and customizing Leaflet popups' - explicitly creates new UI elements within a map. This is a reversible data/configuration modification (code generation), not destructive or executable.
Attacks that exploit this kind of access
Generate code for creating and customizing Leaflet popups with various options and content. It is categorised as a Write tool in the Leaflet MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Leaflet MCP server in PolicyLayer and add a rule for add_popup: 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 Leaflet. Nothing to install.
add_popup is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_popup 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 add_popup. 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.
add_popup is provided by the Leaflet MCP server (philgebauer/leaflet-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 →