AI agents call get_trace_nodes to retrieve information from Openl without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves trace node information during an active trace session. It performs a read-only query to navigate and inspect trace nodes without modifying, creating, or deleting any data. The operation is non-destructive and has no side effects on the system state.
From the tool's definition Tool description explicitly states 'Get trace node children' which is a retrieval operation. The phrase 'get' combined with 'children' indicates a query/fetch operation with no side effects.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Get trace node children (or root nodes if nodeId omitted). Use openl_start_trace first. While the trace is still running the backend answers 409 Conflict; by DEFAULT this tool subscribes to the studio. It is categorised as a Read tool in the Openl MCP Server, which means it retrieves data without modifying state.
Register the Openl MCP server in PolicyLayer and add a rule for get_trace_nodes: 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 Openl. Nothing to install.
get_trace_nodes 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_trace_nodes 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_trace_nodes. 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_trace_nodes is provided by the Openl MCP server (openl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →