Delete a bookmark by ID.
AI agents call pbir_delete_bookmark to permanently remove resources in Power BI Report MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Bookmarks in Power BI reports are user-facing navigation and state-capture objects; deleting one by ID is an irreversible action that removes saved report navigation states. This fits the Destructive category as the action cannot be undone and affects report usability.
From the tool's definition Tool name 'pbir_delete_bookmark' and description 'Delete a bookmark by ID' explicitly state irreversible deletion of a bookmark object from a Power BI report file.
Attacks that exploit this kind of access
Delete a bookmark by ID. It is categorised as a Destructive tool in the Power BI Report MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Power BI Report MCP Server MCP server in PolicyLayer and add a rule for pbir_delete_bookmark: 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 Report MCP Server. Nothing to install.
pbir_delete_bookmark is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the pbir_delete_bookmark 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 pbir_delete_bookmark. 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.
pbir_delete_bookmark is provided by the Power BI Report MCP Server MCP server (jonathan-pap/powerbi-report-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 →