Medium Risk

create_structure

Create atomic/crystal structure from formula, CIF, or XYZ data.

How to control create_structure ↓

What create_structure does on Abacus

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

Medium Risk

Why create_structure needs a policy

This tool creates or initializes computational structure objects used as inputs for downstream scientific calculations. Creation of data structures is a Write operation. While it modifies state, the action is reversible (structures can be modified or replaced), no irreversible deletions occur, no code is executed against external systems, and no financial or destructive operations are performed.

From the tool's definition Tool name 'create_structure' and description 'Create atomic/crystal structure from formula, CIF, or XYZ data' indicates generation of new computational chemistry structure data that is reversible and does not execute calculations, delete data, or move…

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

How to control create_structure

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

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

create_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 Abacus — 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.

Related tools and policies

Go deeper

Questions about create_structure

What does the create_structure tool do? +

Create atomic/crystal structure from formula, CIF, or XYZ data. It is categorised as a Write tool in the Abacus 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_structure? +

Register the Abacus MCP server in PolicyLayer and add a rule for create_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 Abacus. Nothing to install.

What risk level is create_structure? +

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

Can I rate-limit create_structure? +

Yes. Add a rate_limit block to the create_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_structure completely? +

Set action: deny in the PolicyLayer policy for create_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_structure? +

create_structure is provided by the Abacus MCP server (phelanshao/abacus-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 Abacus tool call.

Start from Abacus, 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.

22 Abacus 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.