AI agents use save_document to create or update resources in DOCX-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your DOCX-MCP environment.
The save_document tool modifies the persistent state of a document file by committing edits to storage. This is a Write operation (creates or modifies data reversibly) rather than Read (no side effects) or Destructive (irreversible deletion). The severity is medium because unsupervised saving could overwrite important document versions, but the operation is reversible through version history or recovery.
From the tool's definition Tool name 'save_document' and description 'Save a Word document' indicates persistence of document modifications to storage. This is a write operation that commits changes to disk.
Documented attack patterns abuse exactly the kind of access save_document gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and DOCX-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for save_document:
{
"version": "1",
"default": "deny",
"tools": {
"save_document": {
"limits": [
{
"counter": "save_document_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}save_document stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Save a Word document. It is categorised as a Write tool in the DOCX-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the DOCX- MCP server in PolicyLayer and add a rule for save_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 DOCX-MCP. Nothing to install.
save_document 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_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 save_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.
save_document is provided by the DOCX- MCP server (rookie0x80/docx-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from DOCX-MCP, 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.
16 DOCX-MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.