AI agents call get_plugin_name to retrieve information from Flai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about plugin state without creating, modifying, deleting, or executing any operations. It has no side effects and poses minimal risk even if called repeatedly or with incorrect arguments. The worst outcome is returning stale or incorrect plugin name information, which does not harm the FL Studio session or any external systems.
From the tool's definition Tool name is 'get_plugin_name' and description states 'Get the name of the plugin loaded in a channel.' The verb 'Get' and lack of any modification language indicates a read-only query operation.
Attacks that exploit this kind of access
Get the name of the plugin loaded in a channel. It is categorised as a Read tool in the Flai MCP Server, which means it retrieves data without modifying state.
Register the Flai MCP server in PolicyLayer and add a rule for get_plugin_name: 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 Flai. Nothing to install.
get_plugin_name 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 get_plugin_name 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 get_plugin_name. 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.
get_plugin_name is provided by the Flai MCP server (kaupau/flai-mcp). 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 →