AI agents invoke run_macro to trigger actions in Libreoffice. 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.
The 'run_macro' tool executes user-defined or embedded macros, which can perform arbitrary operations on documents and potentially interact with the file system or external processes. This is an Execute-class tool because the effects depend entirely on the macro code being executed.
From the tool's definition Tool name 'run_macro' combined with server context indicating LibreOffice document interaction. Macros in LibreOffice (typically written in Basic, Python, or JavaScript) execute arbitrary code within the application's security context.
Documented attack patterns abuse exactly the kind of access run_macro 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 run_macro:
{
"version": "1",
"default": "deny",
"tools": {
"run_macro": {
"limits": [
{
"counter": "run_macro_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_macro 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.
run_macro. It is categorised as a Execute tool in the Libreoffice MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Libreoffice MCP server in PolicyLayer and add a rule for run_macro: 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.
run_macro 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 run_macro 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 run_macro. 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.
run_macro 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.