find_replace_formatted
AI agents use find_replace_formatted 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.
Based on the tool name, this likely modifies document content by finding text and replacing it with formatted alternatives, which is a Write operation. The server context (OOXML-level document manipulation) and sibling tools suggest document editing capabilities. Severity is high because bulk find-replace could alter large portions of a document irreversibly in practice, though technically reversible.
From the tool's definition Tool name 'find_replace_formatted' suggests find-and-replace operations with formatting on Word documents; description is empty.
Documented attack patterns abuse exactly the kind of access find_replace_formatted 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 find_replace_formatted:
{
"version": "1",
"default": "deny",
"tools": {
"find_replace_formatted": {
"limits": [
{
"counter": "find_replace_formatted_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} find_replace_formatted 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.
find_replace_formatted. 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 find_replace_formatted: 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.
find_replace_formatted 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 find_replace_formatted 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 find_replace_formatted. 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.
find_replace_formatted 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.