AI agents use reject_draft to create or update resources in Novyx — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Novyx environment.
Rejecting a draft is a write operation—it changes the status of an existing entity reversibly without permanently deleting it. The action can theoretically be undone by resubmitting or creating a new draft. This is less severe than destructive (no permanent deletion) and does not execute arbitrary code or move money.
From the tool's definition The tool 'reject_draft' modifies state by rejecting a draft (a reversible operation that changes the draft's status), which constitutes a write action.
Documented attack patterns abuse exactly the kind of access reject_draft gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Novyx, and nothing reaches the server without passing your rules. This is the rule we recommend for reject_draft:
{
"version": "1",
"default": "deny",
"tools": {
"reject_draft": {
"limits": [
{
"counter": "reject_draft_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}reject_draft 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 a draft without creating a memory. It is categorised as a Write tool in the Novyx MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Novyx MCP server in PolicyLayer and add a rule for reject_draft: 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 Novyx. Nothing to install.
reject_draft 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_draft 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_draft. 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_draft is provided by the Novyx MCP server (novyxlabs/novyx-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 120 Novyx tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
120 Novyx tools catalogued and risk-classified — across an index of 42,500+ MCP servers.