Watch a document for changes and provide live updates
AI agents call watch_document_changes to retrieve information from LibreOffice MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries the current state of a document to detect and report changes. It has no side effects—it does not create, modify, delete, or execute operations. It functions as a listener/monitor that reads document state, placing it squarely in the Read category with low severity and blast radius.
From the tool's definition The tool 'watch_document_changes' is described as monitoring a document and providing 'live updates' on changes.
Attacks that exploit this kind of access
Watch a document for changes and provide live updates. It is categorised as a Read tool in the LibreOffice MCP Server MCP Server, which means it retrieves data without modifying state.
Register the LibreOffice MCP Server MCP server in PolicyLayer and add a rule for watch_document_changes: 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 MCP Server. Nothing to install.
watch_document_changes 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 watch_document_changes 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 watch_document_changes. 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.
watch_document_changes is provided by the LibreOffice MCP Server MCP server (jwingnut/mcp-libre). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →