Export trace as plain text. Returns full trace content. Use release: true to clear trace from memory after export. While the trace is still running the backend answers 409 Conflict; by DEFAULT this tool subscribes to the studio
AI agents call export_trace 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.
The primary function is exporting/reading trace data as plain text. The 'release: true' option clears the trace from memory, which is a minor side effect but the core action is retrieving/reading data. The 409 Conflict behavior and subscription mechanism are operational details that don't elevate the category. Severity is low since it only reads trace/debug information.
From the tool's definition Export trace as plain text. Returns full trace content. Use release: true to clear trace from memory after export.
Attacks that exploit this kind of access
Export trace as plain text. Returns full trace content. Use release: true to clear trace from memory after export. 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 export_trace: 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.
export_trace 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 export_trace 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 export_trace. 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.
export_trace 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 →