Medium Risk

set_active_brain

Set the active brain for subsequent operations

How to control set_active_brain ↓

What set_active_brain does on TheBrain MCP Server

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

Medium Risk

Why set_active_brain needs a policy

This tool creates or modifies configuration/state rather than simply retrieving data (Read). It does not delete data irreversibly (Destructive), execute arbitrary code (Execute), or move money (Financial). While it changes state, the effect is reversible—the active brain can be changed back to a different one. Therefore, it qualifies as Write.

From the tool's definition The tool 'set_active_brain' modifies the state of the system by changing which brain is 'active for subsequent operations.' This is a state-changing operation that affects how other tools will behave going forward.

Documented attack patterns abuse exactly the kind of access set_active_brain gives an agent:

How to control set_active_brain

PolicyLayer is an MCP gateway — it sits between your AI agents and TheBrain MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for set_active_brain:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "set_active_brain": {
      "limits": [
        {
          "counter": "set_active_brain_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

set_active_brain 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.

  1. Create a free account and register TheBrain MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about set_active_brain

What does the set_active_brain tool do? +

Set the active brain for subsequent operations. It is categorised as a Write tool in the TheBrain MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on set_active_brain? +

Register the TheBrain MCP Server MCP server in PolicyLayer and add a rule for set_active_brain: 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 TheBrain MCP Server. Nothing to install.

What risk level is set_active_brain? +

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

Can I rate-limit set_active_brain? +

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

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

set_active_brain is provided by the TheBrain MCP Server MCP server (redmorestudio/thebrain-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every TheBrain MCP Server tool call.

Start from TheBrain MCP Server, 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.

26 TheBrain MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.