AI agents call get_intervention to retrieve information from Novyx without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves an existing supervisor intervention record by its identifier. It performs a simple lookup/query operation without modifying, deleting, executing code, or causing any other state changes. Even in the context of a governance/audit system, retrieving intervention metadata is a read-only action with minimal blast radius if misused.
From the tool's definition Tool name contains 'get' and description states 'Get a supervisor intervention by ID' — a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access get_intervention 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 get_intervention:
{
"version": "1",
"default": "deny",
"tools": {
"get_intervention": {}
}
}get_intervention is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get a supervisor intervention by ID. It is categorised as a Read tool in the Novyx MCP Server, which means it retrieves data without modifying state.
Register the Novyx MCP server in PolicyLayer and add a rule for get_intervention: 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.
get_intervention is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_intervention 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 get_intervention. 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.
get_intervention 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.