gamma_variate
AI agents call gamma_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.
Generating random numbers is a read operation with no side effects—it retrieves/generates data without modifying external state or triggering external operations. The tool does not create, modify, delete, execute code, or commit financial obligations. It only returns computed random values. Severity is low because misuse of RNG would have minimal real-world impact (noise in outputs, at worst).
From the tool's definition Tool name 'gamma_variate' and server context indicate generation of random values from a gamma distribution, with no description provided. This is a mathematical RNG utility consistent with sibling tools (bernoulli_variate, beta_variate, binomial_variate, etc.
Attacks that exploit this kind of access
gamma_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 gamma_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.
gamma_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 gamma_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 gamma_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.
gamma_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 →