Reject all tracked changes in document order.
AI agents use reject_all_changes 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.
This tool modifies a Word document by rejecting tracked changes, which is a reversible write operation. It does not permanently delete data (making it not Destructive), does not execute arbitrary code (not Execute), and does not involve financial transactions (not Financial).
From the tool's definition 'reject_all_changes' rejects tracked changes in a Word document. The description states it operates on 'tracked changes,' which are reversible modifications to document state.
Documented attack patterns abuse exactly the kind of access reject_all_changes 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 reject_all_changes:
{
"version": "1",
"default": "deny",
"tools": {
"reject_all_changes": {
"limits": [
{
"counter": "reject_all_changes_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} reject_all_changes 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.
Reject all tracked changes in document order. 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 reject_all_changes: 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.
reject_all_changes 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 reject_all_changes 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 reject_all_changes. 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.
reject_all_changes 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.