A tool to perform the Mann-Whitney U test for two independent samples
AI agents call mann_whitney_u_test to retrieve information from JeffersonStats without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The Mann-Whitney U test is a hypothesis test that analyzes and compares two independent samples to determine if distributions differ significantly. This is a read-only statistical operation that retrieves/computes descriptive insights from data without creating, modifying, or deleting records. It has no execution, financial, or destructive capabilities.
From the tool's definition Tool performs statistical analysis (Mann-Whitney U test) on provided data without modifying, deleting, or executing arbitrary operations.
Attacks that exploit this kind of access
A tool to perform the Mann-Whitney U test for two independent samples. It is categorised as a Read tool in the JeffersonStats MCP Server, which means it retrieves data without modifying state.
Register the JeffersonStats MCP server in PolicyLayer and add a rule for mann_whitney_u_test: 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 JeffersonStats. Nothing to install.
mann_whitney_u_test 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 mann_whitney_u_test 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 mann_whitney_u_test. 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.
mann_whitney_u_test is provided by the JeffersonStats MCP server (sharabhshukla/jeffersonstatsmcp). 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 →