AI agents use set_secret to create or update resources in Secr — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Secr environment.
set_secret creates or updates secrets, which is a reversible write operation. While this carries high severity due to the sensitive nature of secrets (misuse could expose credentials or modify authentication), it does not irreversibly delete data (which would be Destructive) nor move financial assets (Financial).
From the tool's definition Tool description states 'Create or update a secret' — a reversible modification operation. The server provides 'direct access to secrets management (get, set, list, delete secrets)' with set_secret being the write operation.
Attacks that exploit this kind of access
Create or update a secret. It is categorised as a Write tool in the Secr MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Secr MCP server in PolicyLayer and add a rule for set_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 Secr. Nothing to install.
set_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 set_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 set_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.
set_secret is provided by the Secr MCP server (secr-dev/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 →