Compute descriptive statistics (mean, std, min, max, median, sum, count, skew, kurtosis) on a column.
AI agents call tool_compute_statistics to retrieve information from origin-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads data from a column and computes statistical summaries. It retrieves and analyzes existing data without creating, modifying, or deleting anything. Pure read/query operation with minimal blast radius.
From the tool's definition Compute descriptive statistics (mean, std, min, max, median, sum, count, skew, kurtosis) on a column
Attacks that exploit this kind of access
Compute descriptive statistics (mean, std, min, max, median, sum, count, skew, kurtosis) on a column. It is categorised as a Read tool in the origin-MCP MCP Server, which means it retrieves data without modifying state.
Register the origin- MCP server in PolicyLayer and add a rule for tool_compute_statistics: 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 origin-MCP. Nothing to install.
tool_compute_statistics 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 tool_compute_statistics 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 tool_compute_statistics. 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.
tool_compute_statistics is provided by the origin- MCP server (zhang-923-ze/origin-mcp). 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 →