random_float
AI agents call random_float 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 data without modifying, deleting, executing external operations, or committing financial actions. It is a pure function with no persistent side effects, making it a Read operation. Severity is low because misuse poses minimal risk—an AI agent generating random floats cannot cause harm. The empty description slightly lowers confidence, but the context is clear.
From the tool's definition Tool name 'random_float' and server purpose indicate this generates random floating-point numbers. The Fortuna server is described as 'dedicated to generating high-quality random values' using a C-extension RNG engine.
Attacks that exploit this kind of access
random_float. 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_float: 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_float 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_float 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_float. 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_float 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 →