Recompute the L2 thematic cluster overlay over the decision store using the configured LLM. Stable cluster ids: a fresh cluster whose title matches an existing one (trigram Jaccard >=0.8) updates the existing row in place. Mutates the cluster store; idempotent. Requires an active AI provider — re...
AI agents use build_decision_clusters 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 cluster store by creating, updating, or removing cluster entries. While it's described as idempotent (safe to re-run), it does mutate stored data reversibly — clusters can be recomputed again. This fits the Write category. Severity is medium because misuse could corrupt the decision cluster overlay, but the operation is idempotent and recoverable.
From the tool's definition Mutates the cluster store; idempotent. Stable cluster ids: a fresh cluster whose title matches an existing one... updates the existing row in place.
Documented attack patterns abuse exactly the kind of access build_decision_clusters 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 build_decision_clusters:
{
"version": "1",
"default": "deny",
"tools": {
"build_decision_clusters": {
"limits": [
{
"counter": "build_decision_clusters_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}build_decision_clusters 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.
Recompute the L2 thematic cluster overlay over the decision store using the configured LLM. Stable cluster ids: a fresh cluster whose title matches an existing one (trigram Jaccard >=0.8) updates the existing row in place. Mutates the cluster store; idempotent. Requires an active AI provider — returns a structured error otherwise. Returns JSON: { created, updated, removed, total_after, clusters, strategy_used }. 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 build_decision_clusters: 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.
build_decision_clusters 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 build_decision_clusters 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 build_decision_clusters. 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.
build_decision_clusters 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.