AI agents use keynote_duplicate_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.
Duplicating a slide is a reversible modification operation that creates new content (a copied slide) within the presentation. It does not execute external code, delete data, move money, or read-only query data. The tool belongs in Write category because it creates/modifies presentation state.
From the tool's definition Tool name and description indicate 'Duplicate a slide. The copy is inserted immediately after the original.' — this creates a new slide by copying an existing one, modifying the presentation structure reversibly.
Attacks that exploit this kind of access
Duplicate a slide. The copy is inserted immediately after the original. 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_duplicate_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_duplicate_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_duplicate_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_duplicate_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_duplicate_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 →