Export decisions to JSONL or Markdown. Read-only; no schema mutations. Use for audit, sharing with external tooling, or pre-LLM digestion. JSONL emits one decision per line with
AI agents call export_decisions to retrieve information from Trace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool explicitly states it is read-only with no schema mutations. It exports existing decision data into JSONL or Markdown formats for audit or sharing purposes, making it a pure read/retrieval operation with minimal blast radius.
From the tool's definition Export decisions to JSONL or Markdown. Read-only; no schema mutations. Use for audit, sharing with external tooling, or pre-LLM digestion.
Documented attack patterns abuse exactly the kind of access export_decisions gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trace, and nothing reaches the server without passing your rules. This is the rule we recommend for export_decisions:
{
"version": "1",
"default": "deny",
"tools": {
"export_decisions": {}
}
}export_decisions 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.
Export decisions to JSONL or Markdown. Read-only; no schema mutations. Use for audit, sharing with external tooling, or pre-LLM digestion. JSONL emits one decision per line with. It is categorised as a Read tool in the Trace MCP Server, which means it retrieves data without modifying state.
Register the Trace MCP server in PolicyLayer and add a rule for export_decisions: 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 Trace. Nothing to install.
export_decisions 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_decisions 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_decisions. 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_decisions is provided by the Trace MCP server (nikolai-vysotskyi/trace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 178 Trace tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
178 Trace tools catalogued and risk-classified — across an index of 42,500+ MCP servers.