AI agents use sanitize_metadata to create or update resources in Docx — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Docx environment.
Sanitizing metadata modifies document properties reversibly (author, timestamps, custom fields, etc.) without deletion or financial impact. While the empty description reduces confidence slightly, the context of a document editing MCP server and the action verb 'sanitize' (implying data transformation) places this firmly in Write rather than Read or Destructive.
From the tool's definition Tool name 'sanitize_metadata' on a document editing server implies modification of document metadata; server description emphasizes 'editing...Microsoft Word documents' and 'OOXML-level document manipulation'.
Documented attack patterns abuse exactly the kind of access sanitize_metadata gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Docx, and nothing reaches the server without passing your rules. This is the rule we recommend for sanitize_metadata:
{
"version": "1",
"default": "deny",
"tools": {
"sanitize_metadata": {
"limits": [
{
"counter": "sanitize_metadata_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}sanitize_metadata 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.
sanitize_metadata. It is categorised as a Write tool in the Docx 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 sanitize_metadata: 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. Nothing to install.
sanitize_metadata 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 sanitize_metadata 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 sanitize_metadata. 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.
sanitize_metadata is provided by the Docx MCP server (securityronin/docx-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Docx, 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.
219 Docx tools catalogued and risk-classified — across an index of 43,000+ MCP servers.