Load a dataset from various sources: uploaded files (full path), data directory (filename), URLs, or sklearn datasets
AI agents call load_dataset to retrieve information from MCP DS Toolkit Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Loading data is a read operation with no side effects. It retrieves existing datasets without creating, modifying, or deleting them. The severity is low because loading data poses minimal risk—the worst outcome is accessing unintended data, which is a confidentiality concern but not a destructive or financial risk.
From the tool's definition Tool description states 'Load a dataset from various sources' with no indication of modification, deletion, or execution. The action is purely retrieving/loading data from sources (files, URLs, sklearn datasets).
Attacks that exploit this kind of access
Load a dataset from various sources: uploaded files (full path), data directory (filename), URLs, or sklearn datasets. It is categorised as a Read tool in the MCP DS Toolkit Server MCP Server, which means it retrieves data without modifying state.
Register the MCP DS Toolkit Server MCP server in PolicyLayer and add a rule for load_dataset: 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 MCP DS Toolkit Server. Nothing to install.
load_dataset 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_dataset 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_dataset. 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_dataset is provided by the MCP DS Toolkit Server MCP server (yasserelhaddar/mcp-ds-toolkit-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →