AI agents use dev_rotate_secret to create or update resources in Tru — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tru environment.
This tool creates a new secret and invalidates the old one, which is a reversible modification (a new secret can be rotated again). While the old secret becomes unusable, the action itself is not destructive—no data is deleted, and the system remains functional with the new secret.
From the tool's definition Tool description states 'Rotate the app secret for your tru app' and 'The old secret is immediately invalidated'. This modifies the application's authentication secret, a critical security credential.
Attacks that exploit this kind of access
Rotate the app secret for your tru app. Use this if your secret has been leaked or you need a fresh one. The old secret is immediately invalidated — update TRU_APP_SECRET in your .env right away. It is categorised as a Write tool in the Tru MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tru MCP server in PolicyLayer and add a rule for dev_rotate_secret: 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 Tru. Nothing to install.
dev_rotate_secret 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 dev_rotate_secret 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 dev_rotate_secret. 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.
dev_rotate_secret is provided by the Tru MCP server (tru-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 →