Create a multilevel list in numbering.xml. Each level dict: {num_fmt, lvl_text, indent, hanging, style?}.
AI agents use create_multilevel_list to create or update resources in Docx — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Docx environment.
The tool writes new list formatting definitions to the document's numbering configuration file. This is a structural modification that changes the document's content and presentation, but the changes are reversible (can be undone or edited later).
From the tool's definition Tool creates or modifies document structure by adding a multilevel list to numbering.xml, which is a reversible formatting operation that alters the document's XML configuration.
Documented attack patterns abuse exactly the kind of access create_multilevel_list gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Docx, and nothing reaches the server without passing your rules. This is the rule we recommend for create_multilevel_list:
{
"version": "1",
"default": "deny",
"tools": {
"create_multilevel_list": {
"limits": [
{
"counter": "create_multilevel_list_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_multilevel_list 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.
Free to start. No card required.
Create a multilevel list in numbering.xml. Each level dict: {num_fmt, lvl_text, indent, hanging, style?}. It is categorised as a Write tool in the Docx MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Docx MCP server in PolicyLayer and add a rule for create_multilevel_list: 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 Docx. Nothing to install.
create_multilevel_list 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 create_multilevel_list 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 create_multilevel_list. 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.
create_multilevel_list is provided by the Docx MCP server (securityronin/docx-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Docx, 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.
219 Docx tools catalogued and risk-classified — across an index of 43,000+ MCP servers.