AI agents use pptx_add_textbox 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 creates and inserts a new text box element into a PowerPoint slide, which is a reversible modification of data. It does not execute arbitrary code, delete content, or move money. The blast radius is minimal—a misused instance adds unwanted text boxes to a presentation, which can be easily undone or edited. Therefore, this is categorized as Write with low severity.
From the tool's definition Tool name 'pptx_add_textbox' and description 'Add a text box to a slide' clearly indicate a creation operation that modifies presentation content by inserting a new element.
Attacks that exploit this kind of access
Add a text box to a slide. Position and size in inches. Alignment: left/center/right. Vertical anchor: top/middle/bottom. 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_add_textbox: 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_add_textbox 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_add_textbox 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_add_textbox. 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_add_textbox 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 →