Reject tracked changes — remove insertions, restore deleted text.
AI agents use reject_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.
The tool modifies document state by accepting or rejecting tracked changes, which alters the final document content. However, this is reversible (opposite action could be taken via accept_changes), distinguishing it from Destructive. The operation writes/modifies data but does not permanently delete content—it manages document revisions.
From the tool's definition Tool description states 'Reject tracked changes — remove insertions, restore deleted text.' This modifies document content by reverting insertions and restoring deletions, which are reversible write operations on the document structure.
Documented attack patterns abuse exactly the kind of access reject_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_changes:
{
"version": "1",
"default": "deny",
"tools": {
"reject_changes": {
"limits": [
{
"counter": "reject_changes_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}reject_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 tracked changes — remove insertions, restore deleted 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 reject_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_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_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_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_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.