Manually record an architectural decision, tech choice, preference, or convention. Links to code symbols/files and optionally to a specific subproject for code-aware memory. Decisions have temporal validity — they can be invalidated later when they become outdated. Mutates the decision store (cre...
AI agents use add_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.
The tool creates new decision records in a metadata/memory store. This is a reversible write operation (decisions can be invalidated/updated later as noted). It does not delete data (Destructive), execute arbitrary code (Execute), move money (Financial), or trigger external system operations.
From the tool's definition Tool description states 'Manually record an architectural decision' and 'Mutates the decision store (creates a new record).' The explicit mention of mutation and record creation indicates write operations.
Documented attack patterns abuse exactly the kind of access add_decision 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 add_decision:
{
"version": "1",
"default": "deny",
"tools": {
"add_decision": {
"limits": [
{
"counter": "add_decision_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_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.
Free to start. No card required.
Manually record an architectural decision, tech choice, preference, or convention. Links to code symbols/files and optionally to a specific subproject for code-aware memory. Decisions have temporal validity — they can be invalidated later when they become outdated. Mutates the decision store (creates a new record). For automated extraction from session logs use mine_sessions instead. Returns JSON: { added: { id, title, type } }. 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 add_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.
add_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 add_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 add_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.
add_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.
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.