A tool to calculate z-scores (standard scores) for a collection
AI agents call z_score_calculator 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.
Z-score calculation is a mathematical operation that transforms input data into standardized form. It retrieves no external data, modifies nothing, executes no code or commands, and produces no irreversible changes. This is characteristic of Read category tools—it performs a stateless computation on supplied inputs analogous to a query or fetch operation.
From the tool's definition Tool name 'z_score_calculator' and description 'A tool to calculate z-scores (standard scores) for a collection' indicate a pure calculation/transformation of provided data with no persistence, deletion, code execution, or side effects.
Attacks that exploit this kind of access
A tool to calculate z-scores (standard scores) for a collection. 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 z_score_calculator: 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.
z_score_calculator 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 z_score_calculator 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 z_score_calculator. 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.
z_score_calculator 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 →