AI agents invoke eval_run to trigger actions in Novyx. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
'eval_run' most likely executes code dynamically. Even without a description, the naming convention indicates this is an Execute-category tool. The Novyx governance context (audit, approval workflows, rollback) suggests the tool is intended for controlled execution, but without explicit safeguards documented in the tool description, misuse by an AI agent could trigger unintended code execution.
From the tool's definition Tool name 'eval_run' strongly suggests code evaluation or execution capabilities. Description is empty, but the name pattern (eval_*) is typical for tools that execute arbitrary code or expressions.
Documented attack patterns abuse exactly the kind of access eval_run 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_run:
{
"version": "1",
"default": "deny",
"tools": {
"eval_run": {
"limits": [
{
"counter": "eval_run_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}eval_run stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
eval_run. It is categorised as a Execute tool in the Novyx MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Novyx MCP server in PolicyLayer and add a rule for eval_run: 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_run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the eval_run 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_run. 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_run 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.