Pick one item uniformly at random from a list.
AI agents call random_pick to retrieve information from Nexus Core without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a pure read operation: it selects and returns a random item from an input list without side effects. It neither modifies data, executes code, deletes anything, nor initiates financial transactions. The blast radius of misuse is minimal (worst case: an undesired random choice is made, which is easily corrected).
From the tool's definition Tool description states 'Pick one item uniformly at random from a list' — this is a selection/query operation that retrieves one element from provided data with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Pick one item uniformly at random from a list. It is categorised as a Read tool in the Nexus Core MCP Server, which means it retrieves data without modifying state.
Register the Nexus Core MCP server in PolicyLayer and add a rule for random_pick: 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 Nexus Core. Nothing to install.
random_pick 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 random_pick 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 random_pick. 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.
random_pick is provided by the Nexus Core MCP server (noumenon-ai/nexus-core). 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 →