Low Risk

eval_drift

Detect memory drift over a time period.

How to control eval_drift ↓

AI agents call eval_drift 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.

Low Risk

This tool reads and analyzes memory data to identify inconsistencies or changes ('drift') over time. It performs observational analysis with no side effects—it neither modifies data (Write), executes external operations (Execute), deletes anything (Destructive), nor moves money (Financial).

From the tool's definition Tool name 'eval_drift' and description 'Detect memory drift over a time period' indicate inspection/analysis of existing memory state without modification. The verb 'detect' implies querying or monitoring.

Documented attack patterns abuse exactly the kind of access eval_drift 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 eval_drift:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "eval_drift": {}
  }
}

eval_drift is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Novyx — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the eval_drift tool do? +

Detect memory drift over a time period. It is categorised as a Read tool in the Novyx MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on eval_drift? +

Register the Novyx MCP server in PolicyLayer and add a rule for eval_drift: 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.

What risk level is eval_drift? +

eval_drift is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit eval_drift? +

Yes. Add a rate_limit block to the eval_drift 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.

How do I block eval_drift completely? +

Set action: deny in the PolicyLayer policy for eval_drift. 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.

What MCP server provides eval_drift? +

eval_drift 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.

Enforce policy on every Novyx tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.