poisson_variate
AI agents call poisson_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 random values from a Poisson distribution using the Fortuna RNG engine. It retrieves/computes data (random numbers) without modifying, executing external operations, deleting data, or committing financial transactions. The operation is deterministic in output (random values) with no external side effects or state mutations.
From the tool's definition Tool name 'poisson_variate' indicates generation of Poisson-distributed random variates. No description provided, but context from server description and sibling tools (bernoulli_variate, beta_variate, binomial_variate, etc.) confirms this is a random number…
Attacks that exploit this kind of access
poisson_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 poisson_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.
poisson_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 poisson_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 poisson_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.
poisson_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 →