AI agents call open_document to retrieve information from Libreoffice without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Opening a document typically reads/loads it from disk into memory without modifying it, which is a Read operation. However, the empty description lowers confidence. Severity is medium because opening arbitrary files could expose sensitive data or trigger malicious content.
From the tool's definition Tool name is 'open_document'; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access open_document 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 open_document:
{
"version": "1",
"default": "deny",
"tools": {
"open_document": {}
}
}open_document is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
open_document. It is categorised as a Read tool in the Libreoffice MCP Server, which means it retrieves data without modifying state.
Register the Libreoffice MCP server in PolicyLayer and add a rule for open_document: 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.
open_document is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the open_document 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 open_document. 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.
open_document 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.