AI agents invoke ppt_start_undo_entry to trigger actions in Ppt. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an action in the PowerPoint COM automation layer — specifically initiating an undo transaction boundary. It doesn't read, write, or delete data directly, but executes an operation that affects PowerPoint's internal state/history mechanism. Severity is low since it only marks an undo boundary and doesn't itself cause data changes.
From the tool's definition Start a new undo entry in PowerPoint
Documented attack patterns abuse exactly the kind of access ppt_start_undo_entry gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ppt, and nothing reaches the server without passing your rules. This is the rule we recommend for ppt_start_undo_entry:
{
"version": "1",
"default": "deny",
"tools": {
"ppt_start_undo_entry": {
"limits": [
{
"counter": "ppt_start_undo_entry_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}ppt_start_undo_entry stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Start a new undo entry in PowerPoint. It is categorised as a Execute tool in the Ppt MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ppt MCP server in PolicyLayer and add a rule for ppt_start_undo_entry: 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 Ppt. Nothing to install.
ppt_start_undo_entry is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the ppt_start_undo_entry 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 ppt_start_undo_entry. 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.
ppt_start_undo_entry is provided by the Ppt MCP server (ykuwai/ppt-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 156 Ppt tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
156 Ppt tools catalogued and risk-classified — across an index of 42,500+ MCP servers.