Formats a text item with font, size, color, bold, italic, and alignment options
AI agents use format_text to create or update resources in Keynote MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Keynote MCP Server environment.
This tool modifies existing presentation data (text formatting) but does not delete, destroy, or execute external code. Changes are reversible—text can be reformatted to different styles. The blast radius is medium because an agent could deface or corrupt the visual appearance of slides, but the underlying content remains intact and easily recoverable.
From the tool's definition Tool description states 'Formats a text item with font, size, color, bold, italic, and alignment options' — this modifies presentation content reversibly (text properties can be changed again).
Attacks that exploit this kind of access
Formats a text item with font, size, color, bold, italic, and alignment options. It is categorised as a Write tool in the Keynote MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Keynote MCP Server MCP server in PolicyLayer and add a rule for format_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 MCP Server. Nothing to install.
format_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 format_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 format_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.
format_text is provided by the Keynote MCP Server MCP server (superdwayne/keynotemp). 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 →