percentile_calc
Compute percentiles of a dataset (default p5-p99) and optionally find the percentile rank of a given value.
This record as markdown: /tools/io-github-malamutemayhem-unclick-mcp-server/percentile-calc.md
What percentile_calc does on UnClick
AI agents call percentile_calc to retrieve information from UnClick without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
data | array | Yes | Numeric data array |
value | number | — | Optional value to find its percentile rank |
percentiles | array | — | Percentiles to compute (default [5,10,25,50,75,90,95,99]) |
Parameters from the server's own tool schema.
Why percentile_calc is rated Low
percentile_calc is a stateless mathematical function that processes input data to produce statistical outputs. It retrieves/calculates and queries information without creating, modifying, deleting, or destructively altering any data. This is a classic Read operation with minimal risk profile.
From the tool's definition Tool performs 'Compute percentiles of a dataset' and 'find the percentile rank of a given value' — purely computational analysis with no side effects, data modification, deletion, or external operations.
Attacks that exploit this kind of access
The rule that runs percentile_calc safely
PolicyLayer is an MCP gateway: it sits between your AI agents and UnClick, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For percentile_calc, this is the rule to start with:
percentile_calc is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect UnClick, apply this rule, and every percentile_calc call is checked against it from then on.
Questions about percentile_calc
Compute percentiles of a dataset (default p5-p99) and optionally find the percentile rank of a given value. It is categorised as a Read tool in the UnClick MCP Server, which means it retrieves data without modifying state.
percentile_calc accepts 3 parameters: data, value, percentiles. Required: data. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for percentile_calc: 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 UnClick. Nothing to install.
percentile_calc 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 percentile_calc 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 percentile_calc. 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.
percentile_calc is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on UnClick, and thousands of servers like it.
This server
Across the catalogue