Medium Risk

keynote_format_slide_table

Format cells in a table on a slide (text color, number format)

How to control keynote_format_slide_table ↓

What keynote_format_slide_table does on Iwork

AI agents use keynote_format_slide_table to create or update resources in Iwork — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Iwork environment.

Medium Risk

Why keynote_format_slide_table needs a policy

Formatting table cells (changing text color, applying number formats) modifies presentation content but is fully reversible—users can undo or reformat again. This is a Write operation, not Execute or Destructive. Severity is medium because an AI agent could make numerous unwanted formatting changes affecting document aesthetics and readability, but the changes are non-destructive and easily reverted.

From the tool's definition Tool name indicates 'format' operation on table cells; description specifies formatting modifications: 'text color, number format' — these are reversible style changes to existing data.

Documented attack patterns abuse exactly the kind of access keynote_format_slide_table gives an agent:

How to control keynote_format_slide_table

PolicyLayer is an MCP gateway — it sits between your AI agents and Iwork, and nothing reaches the server without passing your rules. This is the rule we recommend for keynote_format_slide_table:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "keynote_format_slide_table": {
      "limits": [
        {
          "counter": "keynote_format_slide_table_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

keynote_format_slide_table stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Iwork — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about keynote_format_slide_table

What does the keynote_format_slide_table tool do? +

Format cells in a table on a slide (text color, number format). It is categorised as a Write tool in the Iwork MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on keynote_format_slide_table? +

Register the Iwork MCP server in PolicyLayer and add a rule for keynote_format_slide_table: 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 Iwork. Nothing to install.

What risk level is keynote_format_slide_table? +

keynote_format_slide_table is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit keynote_format_slide_table? +

Yes. Add a rate_limit block to the keynote_format_slide_table 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.

How do I block keynote_format_slide_table completely? +

Set action: deny in the PolicyLayer policy for keynote_format_slide_table. 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.

What MCP server provides keynote_format_slide_table? +

keynote_format_slide_table is provided by the Iwork MCP server (reichenbach/iwork_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Iwork tool call.

Start from Iwork, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

114 Iwork tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.