AI agents use set_tempo to create or update resources in Orpheus — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Orpheus environment.
set_tempo creates or modifies project data (tempo setting) reversibly without deleting or executing arbitrary code. While it affects how audio plays back, the change itself is not destructive and can be undone. This is a classic Write category action. Severity is medium because tempo changes could subtly alter the character of a mix or project workflow, but the impact is localized and reversible.
From the tool's definition Tool modifies project state by setting tempo in BPM; operation is reversible via undo or setting a different tempo value. Description explicitly states 'Set the project tempo', a write operation on project configuration.
Attacks that exploit this kind of access
Set the project tempo in BPM (downstream: seconds_per_beat = 60 / bpm). It is categorised as a Write tool in the Orpheus MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Orpheus MCP server in PolicyLayer and add a rule for set_tempo: 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 Orpheus. Nothing to install.
set_tempo 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 set_tempo 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 set_tempo. 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.
set_tempo is provided by the Orpheus MCP server (mal0ware/orpheus). 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 →