bernoulli_variate
AI agents call bernoulli_variate 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 generates and returns random values with no side effects, modifications to persistent state, or external operations triggered. Random value generation is a read-like operation—it retrieves/computes data without altering any system state. The low severity reflects minimal blast radius if misused by an AI agent; an incorrect call simply returns an unwanted random sample.
From the tool's definition Tool name 'bernoulli_variate' indicates generation of random values following a Bernoulli distribution. Server description states the MCP server is 'dedicated to generating high-quality random values' using a 'robust, thread-safe C++ RNG engine'.
Attacks that exploit this kind of access
bernoulli_variate. 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 bernoulli_variate: 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.
bernoulli_variate 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 bernoulli_variate 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 bernoulli_variate. 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.
bernoulli_variate 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 →