AI agents use add_filter to create or update resources in PBIFORGE — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your PBIFORGE environment.
Adding filters/slicers modifies the report structure by introducing new interactive elements, which is a reversible write operation. It does not execute external commands, delete data, or move financial resources. The severity is medium because misuse could alter report behavior unexpectedly, potentially affecting data interpretation, but the changes are reversible and non-destructive.
From the tool's definition Tool description states 'Add a slicer or filter to the report' — this creates or modifies report components reversibly without deleting data or executing arbitrary code.
Attacks that exploit this kind of access
Add a slicer or filter to the report. It is categorised as a Write tool in the PBIFORGE MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the PBIFORGE MCP server in PolicyLayer and add a rule for add_filter: 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 PBIFORGE. Nothing to install.
add_filter 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 add_filter 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 add_filter. 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.
add_filter is provided by the PBIFORGE MCP server (twilize5/reportforge). 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 →