get_datasets
AI agents call get_datasets to retrieve information from PowerBI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves dataset metadata from PowerBI without modifying or deleting any data. However, confidence is not higher because the description is empty, and datasets in PowerBI can potentially contain sensitive business intelligence data, warranting medium severity for unauthorized access risks.
From the tool's definition Tool name is 'get_datasets' and is listed among sibling tools that include 'get_workspaces', 'get_reports', and 'query_dataset' — all read operations. Server description states 'Query workspaces, datasets' indicating retrieval capability.
Attacks that exploit this kind of access
get_datasets. It is categorised as a Read tool in the PowerBI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PowerBI MCP Server MCP server in PolicyLayer and add a rule for get_datasets: 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 PowerBI MCP Server. Nothing to install.
get_datasets 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 get_datasets 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 get_datasets. 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.
get_datasets is provided by the PowerBI MCP Server MCP server (powerbi-mcp). 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 →