Evaluate an estimator using cross-validation on a dataset
AI agents invoke evaluate_estimator to trigger actions in Sktime. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool runs a cross-validation workflow — an active computational process that trains and tests models on data. It executes estimator code against a dataset, which classifies it as Execute. While it doesn't modify or delete data, it triggers potentially expensive computations. Severity is medium because misuse could waste compute resources or produce misleading model evaluations.
From the tool's definition Evaluate an estimator using cross-validation on a dataset
Documented attack patterns abuse exactly the kind of access evaluate_estimator gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Sktime, and nothing reaches the server without passing your rules. This is the rule we recommend for evaluate_estimator:
{
"version": "1",
"default": "deny",
"tools": {
"evaluate_estimator": {
"limits": [
{
"counter": "evaluate_estimator_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}evaluate_estimator stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Evaluate an estimator using cross-validation on a dataset. It is categorised as a Execute tool in the Sktime MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sktime MCP server in PolicyLayer and add a rule for evaluate_estimator: 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 Sktime. Nothing to install.
evaluate_estimator is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the evaluate_estimator 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 evaluate_estimator. 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.
evaluate_estimator is provided by the Sktime MCP server (sktime/sktime-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Sktime, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
24 Sktime tools catalogued and risk-classified — across an index of 43,000+ MCP servers.