AI agents call suggest_plugin to retrieve information from Leaflet without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool provides informational suggestions about available Leaflet plugins. It performs a read-only lookup or search operation without creating, modifying, executing code, deleting data, or moving money. The worst-case misuse (receiving irrelevant or malicious plugin names in recommendations) poses minimal risk since the user must independently evaluate and install any suggested plugins.
From the tool's definition Tool retrieves plugin recommendations based on user input; 'Get recommendations' indicates a query/lookup operation with no side effects or data modification.
Attacks that exploit this kind of access
Get recommendations for Leaflet plugins based on desired functionality or use case. It is categorised as a Read tool in the Leaflet MCP Server, which means it retrieves data without modifying state.
Register the Leaflet MCP server in PolicyLayer and add a rule for suggest_plugin: 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.
suggest_plugin 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 suggest_plugin 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 suggest_plugin. 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.
suggest_plugin 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 →