LLM-driven semantic dedup of the decision store. For each decision in scope, finds top-K similar candidates (FTS + title-trigram) and asks the LLM to merge / replace / invalidate where appropriate. Mutating; respects dry_run (default true). Requires an active AI provider. Returns: { evaluated, ve...
AI agents use consolidate_decisions 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 modifies the decision store by merging, replacing, or invalidating decisions. While 'invalidate' could seem destructive, decisions can potentially be restored and the operation is scoped/controlled with a dry_run flag. The primary action is deduplication via merging and updating records, which is best classified as Write.
From the tool's definition LLM-driven semantic dedup...merge / replace / invalidate where appropriate. Mutating; respects dry_run (default true).
Documented attack patterns abuse exactly the kind of access consolidate_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 consolidate_decisions:
{
"version": "1",
"default": "deny",
"tools": {
"consolidate_decisions": {
"limits": [
{
"counter": "consolidate_decisions_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}consolidate_decisions 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.
LLM-driven semantic dedup of the decision store. For each decision in scope, finds top-K similar candidates (FTS + title-trigram) and asks the LLM to merge / replace / invalidate where appropriate. Mutating; respects dry_run (default true). Requires an active AI provider. Returns: { evaluated, verdicts: [{subject_id, verdict, affected_ids}], applied_count, dry_run }. 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 consolidate_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.
consolidate_decisions 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 consolidate_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 consolidate_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.
consolidate_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.