AI agents call lockbox_get to retrieve information from Clocktower without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves secrets by decrypting them from storage, which is fundamentally a read operation with no modification of data. However, severity is elevated to 'medium' rather than 'low' because unauthorized access to secrets could expose sensitive credentials, API keys, or other authentication material that could be misused by an AI agent if it gains access to them.
From the tool's definition Tool name includes 'get' and description states 'Get (decrypt) a secret from the lockbox' — a retrieval operation.
Documented attack patterns abuse exactly the kind of access lockbox_get gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Clocktower, and nothing reaches the server without passing your rules. This is the rule we recommend for lockbox_get:
{
"version": "1",
"default": "deny",
"tools": {
"lockbox_get": {}
}
} lockbox_get is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get (decrypt) a secret from the lockbox. It is categorised as a Read tool in the Clocktower MCP Server, which means it retrieves data without modifying state.
Register the Clocktower MCP server in PolicyLayer and add a rule for lockbox_get: 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 Clocktower. Nothing to install.
lockbox_get is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the lockbox_get 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 lockbox_get. 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.
lockbox_get is provided by the Clocktower MCP server (sathergate/sathergate-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Clocktower, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
26 Clocktower tools catalogued and risk-classified — across an index of 43,000+ MCP servers.