Save the current state of a document to its file path (or a new path).
AI agents use document_save to create or update resources in LibreOffice MCP Tools — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LibreOffice MCP Tools environment.
This tool creates or modifies data on disk by persisting document changes. It is reversible (the previous file version may exist as a backup, and the file can be edited again), so it is Write rather than Destructive.
From the tool's definition Tool name is 'document_save' and description states 'Save the current state of a document to its file path (or a new path)'. The word 'Save' and action of persisting document state to disk constitutes modification of data.
Attacks that exploit this kind of access
Save the current state of a document to its file path (or a new path). It is categorised as a Write tool in the LibreOffice MCP Tools MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LibreOffice MCP Tools MCP server in PolicyLayer and add a rule for document_save: 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 Tools. Nothing to install.
document_save 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 document_save 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 document_save. 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.
document_save is provided by the LibreOffice MCP Tools MCP server (passerbyflutter/libreoffice-mcp-tools). 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 →