Remove a soundfont from the server.
AI agents call remove_soundfont to permanently remove resources in FluidSynth MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a soundfont deletes it from the server, which cannot be undone without re-adding or re-downloading it. This is an irreversible deletion of a resource, placing it in the Destructive category. Severity is medium since it affects audio rendering capabilities but does not destroy user compositions directly.
From the tool's definition 'Remove a soundfont from the server' — removal of a resource from the server is irreversible without re-downloading
Attacks that exploit this kind of access
Remove a soundfont from the server. It is categorised as a Destructive tool in the FluidSynth MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the FluidSynth MCP Server MCP server in PolicyLayer and add a rule for remove_soundfont: 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 FluidSynth MCP Server. Nothing to install.
remove_soundfont is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_soundfont 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 remove_soundfont. 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.
remove_soundfont is provided by the FluidSynth MCP Server MCP server (kimjune01/synth-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 →