Re-fit decision confidence weights from accumulated review feedback (approve/reject events). Requires >= min_events reviews and at least one of each label. Mutating: when dry_run=false and the fit succeeds, persists to ~/.trace-mcp/confidence_weights.json and resets the in-memory weight cache so ...
AI agents use tune_decision_weights to create or update resources in Trace — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Trace environment.
The tool re-fits and writes updated decision confidence weights to a config file and modifies in-memory state. This is a reversible write operation (the file can be overwritten again), not destructive deletion, not code execution, and not financial.
From the tool's definition persists to ~/.trace-mcp/confidence_weights.json and resets the in-memory weight cache so subsequent remember_decision calls use the new weights
Documented attack patterns abuse exactly the kind of access tune_decision_weights 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 tune_decision_weights:
{
"version": "1",
"default": "deny",
"tools": {
"tune_decision_weights": {
"limits": [
{
"counter": "tune_decision_weights_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}tune_decision_weights stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Re-fit decision confidence weights from accumulated review feedback (approve/reject events). Requires >= min_events reviews and at least one of each label. Mutating: when dry_run=false and the fit succeeds, persists to ~/.trace-mcp/confidence_weights.json and resets the in-memory weight cache so subsequent remember_decision calls use the new weights. Returns: { ok, reason, events_used, weights?, before?, loss_before?, loss_after?, applied }. It is categorised as a Write tool in the Trace MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Trace MCP server in PolicyLayer and add a rule for tune_decision_weights: 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.
tune_decision_weights is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the tune_decision_weights 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 tune_decision_weights. 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.
tune_decision_weights 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.