save
AI agents use save to create or update resources in LibreOffice MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LibreOffice MCP Server environment.
Save operations modify and persist document state. While not destructive (data isn't deleted), this is a Write action—it commits changes made through other tools (edit, insert_text_at_position, etc.) to disk. Severity is high because an AI agent could unknowingly save malicious edits, overwrite critical documents, or corrupt workflows.
From the tool's definition Tool named 'save' on a LibreOffice document server. Given the server's stated capability to 'create, read, edit, and manipulate LibreOffice documents,' the save tool commits document modifications irreversibly to storage.
Attacks that exploit this kind of access
save. It is categorised as a Write tool in the LibreOffice MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LibreOffice MCP Server MCP server in PolicyLayer and add a rule for 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 Server. Nothing to install.
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 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 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.
save 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 →