Creates a new STRATEGIC decision record — architectural choices, technology selections, coding conventions, or project constraints that guide future work across all sessions. Use this ONLY for decisions that would still be relevant if a new session started on a different feature. Do NOT use for b...
AI agents use log_decision to create or update resources in Engrams — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Engrams environment.
This tool creates and stores data (decision records) in a queryable memory system, which is a Write operation. It doesn't retrieve or read existing data (Read), execute arbitrary code (Execute), delete irreversibly (Destructive), or move financial resources (Financial).
From the tool's definition Creates a new STRATEGIC decision record" with required and optional fields (summary, rationale, implementation_details, tags) that are persisted in the system. The tool explicitly accepts structured input and adds data to queryable project memory.
Documented attack patterns abuse exactly the kind of access log_decision gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Engrams, and nothing reaches the server without passing your rules. This is the rule we recommend for log_decision:
{
"version": "1",
"default": "deny",
"tools": {
"log_decision": {
"limits": [
{
"counter": "log_decision_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}log_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.
Creates a new STRATEGIC decision record — architectural choices, technology selections, coding conventions, or project constraints that guide future work across all sessions. Use this ONLY for decisions that would still be relevant if a new session started on a different feature. Do NOT use for bug fixes, code modifications, refactors, or task completions — use log_progress for those. Accepts summary (required), rationale, implementation_details, and tags. The workspace has a configured default visibility (team or individual, set during. It is categorised as a Write tool in the Engrams MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Engrams MCP server in PolicyLayer and add a rule for log_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 Engrams. Nothing to install.
log_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 log_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 log_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.
log_decision is provided by the Engrams MCP server (stevebrownlee/engrams). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Engrams, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
42 Engrams tools catalogued and risk-classified — across an index of 43,000+ MCP servers.