AI agents invoke prev_preset to trigger actions in Flai. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an external operation in FL Studio via Virtual MIDI — navigating to the previous preset of a plugin. It causes a state change in the DAW (changing the active plugin preset), which is an external operation that goes beyond simply reading data or writing a new record. It's not destructive or financial, but it does execute an action that modifies the state of an external system (FL Studio).
From the tool's definition Go back to the previous preset for the plugin in a channel
Attacks that exploit this kind of access
Go back to the previous preset for the plugin in a channel. It is categorised as a Execute tool in the Flai MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Flai MCP server in PolicyLayer and add a rule for prev_preset: 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.
prev_preset is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the prev_preset 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 prev_preset. 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.
prev_preset 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 →