AI agents call random_int to retrieve information from Basic without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/generates a random value and returns it to the caller. It does not create, modify, delete data, execute code, trigger external operations, or move money. While 'random' might suggest unpredictability, the tool itself is deterministic in its behavior (returns a random integer) with no state changes. It falls squarely into the Read category as a value-retrieval operation with no side effects.
From the tool's definition Tool description states 'Generate a cryptographically secure random integer within a range.' The function generates and returns a value with no side effects, modifications to data, or external operations triggered.
Attacks that exploit this kind of access
Generate a cryptographically secure random integer within a range. It is categorised as a Read tool in the Basic MCP Server, which means it retrieves data without modifying state.
Register the Basic MCP server in PolicyLayer and add a rule for random_int: 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 Basic. Nothing to install.
random_int 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_int 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_int. 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_int is provided by the Basic MCP server (msilverblatt/basic-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 →