regression
Linear Regression (least squares) — Best-fit slope, intercept, r^2 and an optional prediction from paired x/y data.
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/regression.md
What regression does on Gateway
AI agents call regression to retrieve information from Gateway 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 |
|---|---|---|---|
x | array | Yes | Array of x values (length >= 2) |
y | array | Yes | Array of y values (same length as x) |
predict_x | number | — | Optional x to predict y for |
Parameters from the server's own tool schema.
Why regression is rated Low
Regression is a statistical analysis function that reads input data (x/y pairs) and computes derived metrics without any side effects. It neither modifies the input data, executes external code, deletes anything, nor commits financial transactions. This is strictly a Read operation—data retrieval and computation only.
From the tool's definition Tool description states 'Linear Regression (least squares) — Best-fit slope, intercept, r^2 and an optional prediction from paired x/y data.' This is a pure mathematical computation that analyzes data and returns statistical results (slope, intercept,…
Attacks that exploit this kind of access
The rule that runs regression safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For regression, this is the rule to start with:
regression 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 Gateway, apply this rule, and every regression call is checked against it from then on.
Questions about regression
Linear Regression (least squares) — Best-fit slope, intercept, r^2 and an optional prediction from paired x/y data. It is categorised as a Read tool in the Gateway MCP Server, which means it retrieves data without modifying state.
regression accepts 3 parameters: x, y, predict_x. Required: x, y. The full parameter table on this page comes from the server's own tool schema.
Register the Gateway MCP server in PolicyLayer and add a rule for regression: 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 Gateway. Nothing to install.
regression 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 regression 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 regression. 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.
regression is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gateway, and thousands of servers like it.
This server
Across the catalogue