AI agents use replace_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.
The tool modifies document content by replacing text, which is a Write-category operation (creates or modifies data reversibly). It is not Destructive because replacements can typically be undone. Severity is medium because an AI agent could introduce text that changes document meaning, legally binding language, or embed malicious content, though the blast radius is contained to the document itself.
From the tool's definition The tool is named 'replace_text' and sits on a Microsoft Word document server (docx-mcp) that 'enables editing...document manipulation.' Replacement of text in a document is a reversible modification operation.
Documented attack patterns abuse exactly the kind of access replace_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 replace_text:
{
"version": "1",
"default": "deny",
"tools": {
"replace_text": {
"limits": [
{
"counter": "replace_text_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}replace_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.
replace_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 replace_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.
replace_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 replace_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 replace_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.
replace_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.