help_commands · PM-MCP (Portfolio Management MCP Server) MCP

WHAT IT DOES

What help_commands does on PM-MCP (Portfolio Management MCP Server)

AI agents call help_commands to retrieve information from PM-MCP (Portfolio Management MCP Server) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

WHY IT NEEDS A POLICY

Why help_commands needs a policy

Help or documentation retrieval tools are informational only, producing no side effects on data or systems. Without a description, confidence is reduced but the name strongly indicates a read-only informational function typical of MCP servers.

From the tool's definition Tool name 'help_commands' with empty description suggests it retrieves or displays available commands/help information. No modification, execution, or destructive capability is implied.

Attacks that exploit this kind of access

Questions about help_commands

What does the help_commands tool do? +

help_commands. It is categorised as a Read tool in the PM-MCP (Portfolio Management MCP Server) MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on help_commands? +

Register the PM-MCP (Portfolio Management MCP Server) MCP server in PolicyLayer and add a rule for help_commands: 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 PM-MCP (Portfolio Management MCP Server). Nothing to install.

What risk level is help_commands? +

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

Can I rate-limit help_commands? +

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

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

help_commands is provided by the PM-MCP (Portfolio Management MCP Server) MCP server (surplus96/pm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.