Ask Fabric MCP to generate a DAX query for the active semantic model. Uses the active semantic model context when no semanticModelId or artifactId is supplied.
AI agents use powerbi_generate_dax_query to create or update resources in Power BI MCP for Claude — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Power BI MCP for Claude environment.
An AI agent can call powerbi_generate_dax_query faster than any human can review — one bad instruction and it creates or modifies resources in Power BI MCP for Claude by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Ask Fabric MCP to generate a DAX query for the active semantic model. Uses the active semantic model context when no semanticModelId or artifactId is supplied. It is categorised as a Write tool in the Power BI MCP for Claude MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Power BI MCP for Claude MCP server in PolicyLayer and add a rule for powerbi_generate_dax_query: 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 Power BI MCP for Claude. Nothing to install.
powerbi_generate_dax_query is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the powerbi_generate_dax_query 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 powerbi_generate_dax_query. 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.
powerbi_generate_dax_query is provided by the Power BI MCP for Claude MCP server (robertoamoreno/powerbi-mcp-claude). 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 →