get-actions

THE RISK

Low Risk

Why get-actions needs a policy

This tool retrieves a list of available actions, likely providing metadata about what operations can be performed. It is purely informational with no capability to create, modify, delete, or execute code. The blast radius from misuse is minimal—an AI could only over-query for information.

From the tool's definition Tool name 'get-actions' and description 'Get available actions' indicate a query/retrieval operation with no side effects. The 'get-' prefix and verb 'Get' are characteristic of Read operations that fetch metadata or configuration without modifying state.

Documented attack patterns abuse exactly the kind of access get-actions gives an agent:

POLICY

How to control get-actions

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get-actions": {}
  }
}

get-actions is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Habitify — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Habitify tools

Destructive delete-habit-log Delete a specific habit log Destructive delete-habit-logs-range Delete habit logs in date range Write add-habit-log Add a habit log Write add-mood Add mood entry Write add-note Add note Read get-areas Get all areas Read get-habit Get habit details Read get-habits Get all habits

All 12 Habitify tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about get-actions

What does the get-actions tool do? +

Get available actions. It is categorised as a Read tool in the Habitify MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get-actions? +

Register the Habitify MCP server in PolicyLayer and add a rule for get-actions: 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 Habitify. Nothing to install.

What risk level is get-actions? +

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

Can I rate-limit get-actions? +

Yes. Add a rate_limit block to the get-actions 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 get-actions completely? +

Set action: deny in the PolicyLayer policy for get-actions. 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 get-actions? +

get-actions is provided by the Habitify MCP server (sargonpiraev/habitify-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Habitify tool call.

Start from Habitify, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →