convex_hull
Compute the convex hull of 2D points with area and perimeter.
This record as markdown: /tools/io-github-malamutemayhem-unclick-mcp-server/convex-hull.md
What convex_hull does on UnClick
AI agents call convex_hull 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 |
|---|---|---|---|
points | array | Yes | Array of [x, y] coordinate pairs. |
Parameters from the server's own tool schema.
Why convex_hull is rated Low
This is a computational geometry function that takes 2D point data as input and returns calculated mathematical results. It performs no I/O beyond returning computed values, does not modify any data, does not execute external commands, and does not have destructive or financial consequences. It is a straightforward Read operation—retrieving/computing derived information from provided input.
From the tool's definition Tool name 'convex_hull' and description 'Compute the convex hull of 2D points with area and perimeter' indicate a pure mathematical computation that reads input points and returns geometric properties (area, perimeter) with no side effects, data modification,…
Attacks that exploit this kind of access
The rule that runs convex_hull 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 convex_hull, this is the rule to start with:
convex_hull 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 convex_hull call is checked against it from then on.
Questions about convex_hull
Compute the convex hull of 2D points with area and perimeter. It is categorised as a Read tool in the UnClick MCP Server, which means it retrieves data without modifying state.
convex_hull accepts 1 parameter: points. Required: points. 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 convex_hull: 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.
convex_hull 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 convex_hull 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 convex_hull. 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.
convex_hull 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