AI agents use pptx_set_slide_background 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 presentation content (slide formatting) but does so reversibly—a background color can be changed back or undone. It does not execute code, delete data, or cause financial impact. The blast radius of misuse is minimal; an incorrect background color is easily corrected. Classified as Write rather than Read (it modifies state) or destructive operations (it is reversible).
From the tool's definition Tool description states it 'Set[s] solid background color for a slide', which is a reversible modification operation.
Attacks that exploit this kind of access
Set solid background color for a slide. Color as hex e.g. '051C2C' (without #). 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_set_slide_background: 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_set_slide_background 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_set_slide_background 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_set_slide_background. 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_set_slide_background 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 →