describe_dataset
AI agents call describe_dataset to retrieve information from MCP Tabular Data Analysis Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the tool name and server context, 'describe_dataset' appears to retrieve metadata or summary information about a dataset (e.g., column names, types, record counts, basic statistics) without modifying data. This is a typical Read operation. Confidence is slightly reduced due to the empty tool description, but the context from sibling tools and server purpose provides strong supporting evidence.
From the tool's definition Tool name 'describe_dataset' and context of sibling tools (analyze_time_series, compute_correlation, detect_anomalies, etc.) indicate data querying and introspection.
Attacks that exploit this kind of access
describe_dataset. It is categorised as a Read tool in the MCP Tabular Data Analysis Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Tabular Data Analysis Server MCP server in PolicyLayer and add a rule for describe_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 Tabular Data Analysis Server. Nothing to install.
describe_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 describe_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 describe_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.
describe_dataset is provided by the MCP Tabular Data Analysis Server MCP server (k02d/mcp-tabular). 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 →