log_decision | PolicyLayer

WHAT IT DOES

What log_decision does on Studio Catharsis Universal Project Coordinator MCP

AI agents use log_decision to create or update resources in Studio Catharsis Universal Project Coordinator MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Studio Catharsis Universal Project Coordinator MCP environment.

WHY IT NEEDS A POLICY

Why log_decision needs a policy

This tool creates and stores new decision records in a shared project state (the decision log). It modifies system state by adding data reversibly—decisions can be reviewed, updated, or marked superseded without physical deletion. This is a Write operation: it creates structured data entries but lacks the irreversibility of Destructive actions or the code-execution risk of Execute.

From the tool's definition Tool description states it 'Record[s] a product or technical decision with rationale. Logs to decision history.' The verb 'log' and 'record' indicate persistent creation of a new decision entry in a decision history database or log.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

log_decision Rate-limited

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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "log_decision": {
      "limits": [
        {
          "counter": "log_decision_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Studio Catharsis Universal Project Coordinator MCP, so you can run agents against it safely.

FAQ

Questions about log_decision

What does the log_decision tool do? +

Record a product or technical decision with rationale. Logs to decision history. It is categorised as a Write tool in the Studio Catharsis Universal Project Coordinator MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on log_decision? +

Register the Studio Catharsis Universal Project Coordinator 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 Studio Catharsis Universal Project Coordinator MCP. Nothing to install.

What risk level is log_decision? +

log_decision is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit log_decision? +

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.

How do I block log_decision completely? +

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.

What MCP server provides log_decision? +

log_decision is provided by the Studio Catharsis Universal Project Coordinator MCP server (studio-catharsis-creative-lab/project_com_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.