AI agents call eval_history 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 queries and returns a list of past evaluation runs from shared memory/audit logs. It is a read-only operation that retrieves information without creating, modifying, deleting, or executing anything. The blast radius is minimal—an AI agent misusing this tool would only see historical data it likely already has context about, with no destructive or operational consequences.
From the tool's definition Tool name 'eval_history' and description 'List past memory evaluation runs' indicate retrieval of historical data with no modification or side effects.
Documented attack patterns abuse exactly the kind of access eval_history 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_history:
{
"version": "1",
"default": "deny",
"tools": {
"eval_history": {}
}
}eval_history 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.
List past memory evaluation runs. 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 eval_history: 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.
eval_history 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 eval_history 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 eval_history. 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.
eval_history 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.