AI agents use apply_style to create or update resources in Libreoffice — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Libreoffice environment.
The tool modifies document formatting (a reversible change to document state) rather than reading, executing code, or destroying data. LibreOffice style application changes document properties but does not execute arbitrary commands, delete content, or move money.
From the tool's definition Tool name 'apply_style' combined with server context indicating LibreOffice document manipulation; sibling tools include 'conditional_format', 'format_cell_range', and 'create_chart', all Write operations on document content.
Documented attack patterns abuse exactly the kind of access apply_style gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Libreoffice, and nothing reaches the server without passing your rules. This is the rule we recommend for apply_style:
{
"version": "1",
"default": "deny",
"tools": {
"apply_style": {
"limits": [
{
"counter": "apply_style_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}apply_style 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.
apply_style. It is categorised as a Write tool in the Libreoffice MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Libreoffice MCP server in PolicyLayer and add a rule for apply_style: 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 Libreoffice. Nothing to install.
apply_style 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 apply_style 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 apply_style. 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.
apply_style is provided by the Libreoffice MCP server (waterpistolai/libreoffice-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Libreoffice, 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.
24 Libreoffice tools catalogued and risk-classified — across an index of 43,000+ MCP servers.