AI agents call list-traces to retrieve information from Phoenix without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'list' verb indicates a query/retrieval operation with no side effects. Traces are typically logs or records that are read for inspection. With empty description, confidence is moderate but the verb semantics and context support Read classification. Severity is low as listing traces poses minimal risk—it provides visibility but does not modify or execute external operations.
From the tool's definition Tool name 'list-traces' contains 'list' verb, which is a typical Read operation that retrieves or queries data. No description provided to suggest side effects.
Documented attack patterns abuse exactly the kind of access list-traces gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Phoenix, and nothing reaches the server without passing your rules. This is the rule we recommend for list-traces:
{
"version": "1",
"default": "deny",
"tools": {
"list-traces": {}
}
}list-traces 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-traces. It is categorised as a Read tool in the Phoenix MCP Server, which means it retrieves data without modifying state.
Register the Phoenix MCP server in PolicyLayer and add a rule for list-traces: 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 Phoenix. Nothing to install.
list-traces 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 list-traces 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 list-traces. 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.
list-traces is provided by the Phoenix MCP server (@Arize-ai/phoenix). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 34 Phoenix tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
34 Phoenix tools catalogued and risk-classified — across an index of 42,500+ MCP servers.