AI agents use pptx_format_shape to create or update resources in Pptx — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pptx environment.
This tool modifies existing shapes in a PowerPoint presentation (reposition, resize, restyle) but does not delete data or execute arbitrary code. The changes are reversible through undo or manual correction. While it alters presentation state, the impact is limited to shape formatting properties without side effects on external systems or destructive data loss.
From the tool's definition Tool description states it can 'Reposition, resize, or restyle an existing shape' - these are reversible modifications to presentation content.
Attacks that exploit this kind of access
Reposition, resize, or restyle an existing shape. Dimensions in inches. It is categorised as a Write tool in the Pptx MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pptx MCP server in PolicyLayer and add a rule for pptx_format_shape: 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 Pptx. Nothing to install.
pptx_format_shape 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 pptx_format_shape 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 pptx_format_shape. 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.
pptx_format_shape is provided by the Pptx MCP server (knorq-ai/pptx-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 →