AI agents use add_notes to create or update resources in Flai — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Flai environment.
This tool creates or modifies notes within a music pattern in FL Studio. While reversible (notes can be deleted/edited afterward), it has write semantics. The severity is medium because misuse by an AI agent could produce unintended music compositions or overwrite creative work, but the impact is limited to a single pattern's note data and poses no financial, destructive system, or code-execution risk.
From the tool's definition Tool name 'add_notes' and description 'Add notes to a pattern without clearing existing notes' indicate creation/modification of music pattern data. The key phrase is 'add notes' which is a reversible write operation that modifies pattern state.
Attacks that exploit this kind of access
Add notes to a pattern without clearing existing notes. It is categorised as a Write tool in the Flai MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Flai MCP server in PolicyLayer and add a rule for add_notes: 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.
add_notes 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_notes 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_notes. 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_notes 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 →