Low Risk

list_categories

List all Griptape Framework sections and Node categories.

How to control list_categories ↓

What list_categories does on Griptape

AI agents call list_categories to retrieve information from Griptape without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why list_categories needs a policy

This tool retrieves structured metadata (categories and sections) from the documentation database without modifying data, triggering external operations, or causing side effects. It is a simple enumeration query aligned with Read category operations like 'list' and 'get'.

From the tool's definition Tool name 'list_categories' and description 'List all Griptape Framework sections and Node categories' indicate a retrieval operation that queries a pre-built SQLite database to enumerate available documentation categories.

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

How to control list_categories

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "list_categories": {}
  }
}

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

  1. Create a free account and register Griptape — 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.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about list_categories

What does the list_categories tool do? +

List all Griptape Framework sections and Node categories. It is categorised as a Read tool in the Griptape MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on list_categories? +

Register the Griptape MCP server in PolicyLayer and add a rule for list_categories: 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 Griptape. Nothing to install.

What risk level is list_categories? +

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

Can I rate-limit list_categories? +

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

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

list_categories is provided by the Griptape MCP server (kiansalem/griptape-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Griptape tool call.

Start from Griptape, 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.

6 Griptape 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.