AI agents call keynote_export_all_slides to retrieve information from Keynote without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads slide content and exports it as PNG image files to a temp directory. It does not modify the presentation, delete data, execute arbitrary code, or involve financial operations. Writing image files to /tmp is a side effect, but it is a standard read/export operation with minimal blast radius — the output is ephemeral temp files derived from existing content.
From the tool's definition Export all slides as PNG images to /tmp/keynote-mcp-export/. Returns the list of file paths.
Attacks that exploit this kind of access
Export all slides as PNG images to /tmp/keynote-mcp-export/. Returns the list of file paths. Use Read on each path to visually analyze slides. It is categorised as a Read tool in the Keynote MCP Server, which means it retrieves data without modifying state.
Register the Keynote MCP server in PolicyLayer and add a rule for keynote_export_all_slides: 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_export_all_slides is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the keynote_export_all_slides 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_export_all_slides. 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_export_all_slides 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 →