Query the decision knowledge graph. Filter by type, subproject, code symbol, file path, tag, or time. Returns decisions linked to code —
AI agents call query_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.
This tool performs read-only operations on a knowledge graph of decisions. It applies filters to retrieve information but produces no side effects, reversible changes, code execution, or irreversible modifications. It is a pure query/search operation analogous to 'list' or 'fetch' in standard categorization.
From the tool's definition Tool name 'query_decisions' and description 'Query the decision knowledge graph. Filter by...' indicate data retrieval with filtering capabilities.
Documented attack patterns abuse exactly the kind of access query_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 query_decisions:
{
"version": "1",
"default": "deny",
"tools": {
"query_decisions": {}
}
}query_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.
Query the decision knowledge graph. Filter by type, subproject, code symbol, file path, tag, or time. Returns decisions linked to code —. 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 query_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.
query_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 query_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 query_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.
query_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.