guidance_brain

SERVERClaude Flow SOURCEclaude-flow

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-ruvnet-claude-flow/guidance-brain.md

WHAT IT DOES

What guidance_brain does on Claude Flow

AI agents call guidance_brain to retrieve information from Claude Flow without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why guidance_brain is rated Low

This tool queries a capability registry and returns recommendations and implementation guidance. It reads/fetches metadata about registered MCP tools (registration, configuration, reachability, health, authorization status) without modifying, deleting, or executing anything. The blast radius of misuse is low since it only surfaces informational guidance.

From the tool's definition 'Queries the live capability brain', 'recommends capabilities', 'returns the validated implementation loop' — purely retrieves and returns guidance/metadata about tools and capabilities

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs guidance_brain safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Flow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For guidance_brain, this is the rule to start with:

guidance_brain Allowed

guidance_brain is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "guidance_brain": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Claude Flow, apply this rule, and every guidance_brain call is checked against it from then on.

FAQ

Questions about guidance_brain

What does the guidance_brain tool do? +

Use when choosing how to execute a task with Ruflo. Queries the live capability brain, covers every registered MCP tool, separates registration from configuration/reachability/health/authorization, recommends capabilities, and returns the validated implementation loop. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on guidance_brain? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for guidance_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 Claude Flow. Nothing to install.

What risk level is guidance_brain? +

guidance_brain is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit guidance_brain? +

Yes. Add a rate_limit block to the guidance_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 guidance_brain completely? +

Set action: deny in the PolicyLayer policy for guidance_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 guidance_brain? +

guidance_brain is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Claude Flow, and thousands of servers like it.

This server

All 496 Claude Flow tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →