Refresh a Power BI dataset
AI agents invoke refresh_dataset to trigger actions in Microsoft Fabric MCP Server. 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.
Refreshing a dataset triggers an external operation that re-executes data ingestion/ETL pipelines against source systems. It is not a simple write (no new data is created by the user) nor purely read. It executes a backend process with side effects (compute costs, source system load, potential data changes in the dataset). Misuse could trigger repeated expensive refreshes or cause downstream report inconsistencies.
From the tool's definition Refresh a Power BI dataset
Attacks that exploit this kind of access
Refresh a Power BI dataset. It is categorised as a Execute tool in the Microsoft Fabric MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Microsoft Fabric MCP Server MCP server in PolicyLayer and add a rule for refresh_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 Microsoft Fabric MCP Server. Nothing to install.
refresh_dataset 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 refresh_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 refresh_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.
refresh_dataset is provided by the Microsoft Fabric MCP Server MCP server (snahrup/microsoft-fabric-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 →