AI agents call get-randomness-by-time to retrieve information from Drand without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the drand network to retrieve a pre-generated random value for a given time. It performs no write operations, does not execute arbitrary code, does not delete data, and does not involve financial transactions. The operation is purely informational with no state changes or external side effects beyond the network read request itself.
From the tool's definition Tool description states 'Get the random value associated with a specific time' which is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get the random value associated with a specific time from drand quicknet. It is categorised as a Read tool in the Drand MCP Server, which means it retrieves data without modifying state.
Register the Drand MCP server in PolicyLayer and add a rule for get-randomness-by-time: 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 Drand. Nothing to install.
get-randomness-by-time 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 get-randomness-by-time 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 get-randomness-by-time. 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.
get-randomness-by-time is provided by the Drand MCP server (randa-mu/drand-mcp-server). 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 →