Get instructions on how to use the available tool groups and services. Call this FIRST when unsure which tool to use, when a user asks
AI agents call guidance to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is fundamentally a Read operation—it retrieves information without modifying state. However, in the context of a server with 87 tools for 'enterprise dev' and agent swarm orchestration, malicious or misleading guidance could redirect an agent toward destructive operations like agent_terminate or unauthorized agent_spawn calls.
From the tool's definition Tool is named 'guidance' and described as retrieving 'instructions on how to use the available tool groups and services'—a read operation that retrieves reference data.
Attacks that exploit this kind of access
Get instructions on how to use the available tool groups and services. Call this FIRST when unsure which tool to use, when a user asks. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for guidance: 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.
guidance is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the guidance 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.
Set action: deny in the PolicyLayer policy for guidance. 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.
guidance 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.