AI agents use redact_text 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.
Redacting text in a Word document is a write operation that modifies document content. While not purely destructive (original data may be recoverable via track changes or by undoing), it materially alters the visible document state. The high severity reflects that careless redaction could expose or hide sensitive information improperly.
From the tool's definition Tool name 'redact_text' combined with server context describing 'editing...Microsoft Word documents' and 'OOXML-level document manipulation'.
Documented attack patterns abuse exactly the kind of access redact_text 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 redact_text:
{
"version": "1",
"default": "deny",
"tools": {
"redact_text": {
"limits": [
{
"counter": "redact_text_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}redact_text 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.
redact_text. 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 redact_text: 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.
redact_text 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 redact_text 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 redact_text. 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.
redact_text 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.