routines · Personal Brain MCP: Risk & Policy

WHAT IT DOES

What routines does on Personal Brain

AI agents use routines to create or update resources in Personal Brain — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Personal Brain environment.

WHY IT NEEDS A POLICY

Why routines needs a policy

This tool modifies personal routine data within the user's personal-brain database. While it creates or updates structured checklist information, it does not execute external commands, delete data irreversibly, or affect financial/critical systems. The blast radius of misuse is limited to corrupting or altering personal routine records, which are reversible. Hence, Write is the appropriate category with low severity.

From the tool's definition Tool description explicitly states 'Manage routines and their ordered steps,' indicating creation and modification of routine data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

routines Rate-limited

routines 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": {
    "routines": {
      "limits": [
        {
          "counter": "routines_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 Personal Brain, so you can run agents against it safely.

FAQ

Questions about routines

What does the routines tool do? +

Event-invoked checklists (morning routine, leaving for a trip, closing the cabin). Manage routines and their ordered steps. It is categorised as a Write tool in the Personal Brain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on routines? +

Register the Personal Brain MCP server in PolicyLayer and add a rule for routines: 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 Personal Brain. Nothing to install.

What risk level is routines? +

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

Can I rate-limit routines? +

Yes. Add a rate_limit block to the routines 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 routines completely? +

Set action: deny in the PolicyLayer policy for routines. 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 routines? +

routines is provided by the Personal Brain MCP server (phantomts/personal-brain-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.