random_range
AI agents call random_range to retrieve information from FortunaMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/generates random numerical data with no side effects on external systems or data stores. It is a pure computational function that returns values without modifying state, creating obligations, or executing arbitrary operations. Random value generation is a Read category operation—it queries the RNG engine for output.
From the tool's definition Tool name 'random_range' indicates generation of random numbers within a specified range. The server is explicitly dedicated to 'generating high-quality random values' using the Fortuna CSPRNG engine.
Attacks that exploit this kind of access
random_range. It is categorised as a Read tool in the FortunaMCP MCP Server, which means it retrieves data without modifying state.
Register the Fortuna MCP server in PolicyLayer and add a rule for random_range: 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 FortunaMCP. Nothing to install.
random_range 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_range 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_range. 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_range is provided by the Fortuna MCP server (siliconsociety/fortunamcp). 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 →