ultrabrain_branch · Ultrabrain MCP: Risk & Policy

WHAT IT DOES

What ultrabrain_branch does on Ultrabrain

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

WHY IT NEEDS A POLICY

Why ultrabrain_branch needs a policy

This tool creates new branches in a reasoning/thought system, which is a write operation that modifies internal state. It is reversible (branches can be deleted or replaced) and has no destructive or external side effects.

From the tool's definition Tool description states 'Create or continue an Ultrabrain branch from a prior thought.' The verb 'create' indicates data creation; 'branch' and 'continue' suggest reversible modifications to reasoning state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ultrabrain_branch Rate-limited

ultrabrain_branch 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": {
    "ultrabrain_branch": {
      "limits": [
        {
          "counter": "ultrabrain_branch_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 Ultrabrain, so you can run agents against it safely.

FAQ

Questions about ultrabrain_branch

What does the ultrabrain_branch tool do? +

Create or continue an Ultrabrain branch from a prior thought. It is categorised as a Write tool in the Ultrabrain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on ultrabrain_branch? +

Register the Ultrabrain MCP server in PolicyLayer and add a rule for ultrabrain_branch: 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 Ultrabrain. Nothing to install.

What risk level is ultrabrain_branch? +

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

Can I rate-limit ultrabrain_branch? +

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

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

ultrabrain_branch is provided by the Ultrabrain MCP server (lcv-ideas-software/ultrabrain-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.