Inject mapped fields into PBIP structure and generate the dashboard.
AI agents use inject_pbip to create or update resources in powerBI-mcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your powerBI-mcp environment.
The tool writes data into PBIP files and generates a Power BI dashboard, which is a reversible file-creation/modification operation. It does not execute arbitrary code or delete data, but misuse could overwrite existing dashboard files or inject malicious content into reports, warranting a high severity rating.
From the tool's definition 'Inject mapped fields into PBIP structure and generate the dashboard' — creates/modifies PBIP files and generates a new dashboard artifact
Attacks that exploit this kind of access
Inject mapped fields into PBIP structure and generate the dashboard. It is categorised as a Write tool in the powerBI-mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the powerBI- MCP server in PolicyLayer and add a rule for inject_pbip: 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. Nothing to install.
inject_pbip 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 inject_pbip 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 inject_pbip. 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.
inject_pbip is provided by the powerBI- MCP server (ramandimbinirina/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 →