Execute DAX query against a dataset
AI agents invoke query_dataset to trigger actions in PowerBI 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.
DAX queries are executed against a PowerBI dataset at runtime; the tool runs arbitrary code (DAX expressions) rather than performing a simple pre-defined read. Depending on the query, it could expose sensitive data, trigger expensive computations, or be crafted maliciously.
From the tool's definition "Execute DAX query against a dataset" — the word 'Execute' and 'query' against a dataset indicate running arbitrary DAX expressions, which can perform complex calculations, data extraction, and potentially invoke DAX functions with side effects.
Attacks that exploit this kind of access
Execute DAX query against a dataset. It is categorised as a Execute tool in the PowerBI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PowerBI MCP Server MCP server in PolicyLayer and add a rule for query_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 PowerBI MCP Server. Nothing to install.
query_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 query_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 query_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.
query_dataset is provided by the PowerBI MCP Server MCP server (pkduongsu/powerbi-mcp-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 →