consolidate_decisions
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...
This record as markdown: /tools/nikolai-vysotskyi-trace-mcp/consolidate-decisions.md
What consolidate_decisions does on Trace
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.
Why consolidate_decisions is rated Medium
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).
Attacks that exploit this kind of access
The rule that runs consolidate_decisions safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Trace, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For consolidate_decisions, this is the rule to start with:
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.
The button opens the PolicyLayer dashboard: create your workspace, connect Trace, apply this rule, and every consolidate_decisions call is checked against it from then on.
Questions about consolidate_decisions
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.
More on Trace, and thousands of servers like it.
This server
Across the catalogue