Load data from various sources into a data handle for forecasting.
AI agents call load_data_source to retrieve information from Sktime without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or ingests data from sources and makes it available for downstream processing. It has no side effects on the source or on the system state beyond making data accessible. While it interacts with external data sources, it is fundamentally a Read operation similar to 'fetch' or 'get'.
From the tool's definition Tool description states 'Load data from various sources into a data handle' — a retrieval operation that reads data without modification or deletion. The verb 'load' indicates fetching/ingesting data, not executing arbitrary code or modifying state.
Documented attack patterns abuse exactly the kind of access load_data_source 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 load_data_source:
{
"version": "1",
"default": "deny",
"tools": {
"load_data_source": {}
}
}load_data_source is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Load data from various sources into a data handle for forecasting. It is categorised as a Read tool in the Sktime MCP Server, which means it retrieves data without modifying state.
Register the Sktime MCP server in PolicyLayer and add a rule for load_data_source: 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.
load_data_source 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 load_data_source 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 load_data_source. 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.
load_data_source 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.