Medium Risk

create_people_definition

create_people_definition

How to control create_people_definition ↓

What create_people_definition does on Openstudio

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

Medium Risk

Why create_people_definition needs a policy

This tool creates a new people definition object within an OpenStudio energy model, which is a reversible modification of model data. This is a Write-category action (creates model data) rather than Read (no query), Execute (no external command), Destructive (reversible), or Financial (no monetary impact).

From the tool's definition Tool name is 'create_people_definition' indicating creation of a new data object. Server description states it enables 'creation, querying, and modification of models'. The 'create_' prefix confirms write/creation semantics.

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

How to control create_people_definition

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

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

create_people_definition 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 Openstudio — 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_people_definition

What does the create_people_definition tool do? +

create_people_definition. It is categorised as a Write tool in the Openstudio 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_people_definition? +

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

What risk level is create_people_definition? +

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

Can I rate-limit create_people_definition? +

Yes. Add a rate_limit block to the create_people_definition 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_people_definition completely? +

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

create_people_definition is provided by the Openstudio MCP server (natlabrockies/openstudio-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Openstudio tool call.

Start from Openstudio, 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.

146 Openstudio 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.