Switch the default TTS engine.
AI agents use set_engine to create or update resources in Voice Bridge — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Voice Bridge environment.
This tool creates or modifies settings (the default TTS engine selection) in a reversible manner. It does not read data, execute external code, destroy data, or involve financial transactions. The blast radius is minimal—a mistaken engine switch merely changes which voice synthesis backend is used, easily reverted by calling set_engine again with the correct engine name.
From the tool's definition Tool name 'set_engine' indicates it modifies configuration state by switching the default TTS engine. The description states the tool changes which engine is used, a reversible configuration update.
Attacks that exploit this kind of access
Switch the default TTS engine. It is categorised as a Write tool in the Voice Bridge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Voice Bridge MCP server in PolicyLayer and add a rule for set_engine: 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 Voice Bridge. Nothing to install.
set_engine 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_engine 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_engine. 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_engine is provided by the Voice Bridge MCP server (Tomorrow-You/voice-bridge). 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 →