Medium Risk

create_node_structure

Create a complex node structure with nested children. Pass a JSON object conforming to the Tana API node format.

How to control create_node_structure ↓

AI agents use create_node_structure to create or update resources in Tana MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tana MCP Server environment.

Medium Risk

This tool creates and inserts data into Tana workspaces. While it does not delete or permanently destroy data (Destructive), it does reversibly create and modify workspace content. The high severity reflects that an AI agent could inadvertently create large volumes of unwanted nested data structures, pollute the workspace, or create data that requires manual cleanup.

From the tool's definition Tool name is 'create_node_structure' and description states it is designed to 'Create a complex node structure with nested children' by passing a JSON object to the Tana API.

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

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_node_structure": {
      "limits": [
        {
          "counter": "create_node_structure_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

create_node_structure stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Tana MCP Server — 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.
LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the create_node_structure tool do? +

Create a complex node structure with nested children. Pass a JSON object conforming to the Tana API node format. It is categorised as a Write tool in the Tana MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_node_structure? +

Register the Tana MCP Server MCP server in PolicyLayer and add a rule for create_node_structure: 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 Tana MCP Server. Nothing to install.

What risk level is create_node_structure? +

create_node_structure is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_node_structure? +

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

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

create_node_structure is provided by the Tana MCP Server MCP server (tim-mcdonnell/tana-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Tana MCP Server tool call.

Deterministic rules across all 12 Tana MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

12 Tana MCP Server tools catalogued and risk-classified — across an index of 42,500+ 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.