remember_decision
Live agent write into the decision knowledge graph. Confidence-scores the input and routes it through the memoir review queue: high-confidence rows enter the active graph immediately, mid-confidence rows queue for human approval, low-confidence rows are dropped without persistence. Per-session de...
This record as markdown: /tools/nikolai-vysotskyi-trace-mcp/remember-decision.md
What remember_decision does on Trace
AI agents use remember_decision 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 remember_decision is rated Medium
This tool modifies data by writing decision records into a persistent knowledge graph. The operation is reversible (decisions can be updated or removed via other tools like add_decision or administrative actions), making it Write rather than Destructive.
From the tool's definition Tool performs 'write into the decision knowledge graph' with routing through 'review queue' and persistent storage ('enter the active graph immediately', 'queue for human approval').
Attacks that exploit this kind of access
The rule that runs remember_decision 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 remember_decision, this is the rule to start with:
remember_decision 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 remember_decision call is checked against it from then on.
Questions about remember_decision
Live agent write into the decision knowledge graph. Confidence-scores the input and routes it through the memoir review queue: high-confidence rows enter the active graph immediately, mid-confidence rows queue for human approval, low-confidence rows are dropped without persistence. Per-session dedup + rate-limit. Use during a session to capture decisions in real time. For manual high-confidence writes use add_decision; for post-hoc extraction from session logs use mine_sessions. Returns JSON: { id, review_status, confidence, deduplicated? }. 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 remember_decision: 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.
remember_decision 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 remember_decision 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 remember_decision. 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.
remember_decision 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