AI agents use keynote_set_text 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.
This tool modifies presentation content by replacing text on slides, which is a Write operation. It is reversible and has no permanent deletion or financial implications. Severity is medium because misuse could corrupt presentation content, but the blast radius is limited to a single presentation file that can be recovered from backups or undo operations.
From the tool's definition Tool name 'keynote_set_text' and description 'Replace the text content of a text element on a slide' directly indicates modification of existing data.
Attacks that exploit this kind of access
Replace the text content of a text element on a slide. Preserves existing font styling. 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_set_text: 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_set_text 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_set_text 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_set_text. 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_set_text 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 →