AI agents use keynote_add_slide to create or update resources in Keynote — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Keynote environment.
Adding a slide creates new content within a Keynote presentation, making it a Write operation. The change is reversible (slides can be deleted), so it does not qualify as Destructive. Severity is medium because while the operation modifies user content, it is non-destructive and bounded in scope—it only adds a blank slide without executing arbitrary code or affecting external systems.
From the tool's definition Tool description states 'Add a new blank slide at the end of the presentation.' This is a create operation that modifies the presentation by adding new content.
Attacks that exploit this kind of access
Add a new blank slide at the end of the presentation. It is categorised as a Write tool in the Keynote MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Keynote MCP server in PolicyLayer and add a rule for keynote_add_slide: 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 Keynote. Nothing to install.
keynote_add_slide 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 keynote_add_slide 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 keynote_add_slide. 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.
keynote_add_slide is provided by the Keynote MCP server (tszaks/keynote-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 →