New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

create_needs_system

Generate a sim/tycoon needs engine component: a [Property] list of need definitions (name, decay rate/s, critical threshold, weight) with per-need 0..100 values that decay over Time.Delta, Satisfy(name, amount) to restore, an aggregate Happiness (weighted mean, [Sync(FromHost)] when networked), a...

SERVERSbox SOURCEsbox-mcp-server
Medium RISK CLASS
Category Write
Parameters 00 required
Recommended Rate-limitedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/sbox/create-needs-system.md

What create_needs_system does on Sbox

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

Why create_needs_system is rated Medium

Creates and modifies game state data via component properties, events, and networked synchronization—a reversible write operation.

From the tool's definition Generate sim/tycoon needs engine component with property list, decay rates, events

Questions about create_needs_system

What does the create_needs_system tool do? +

Generate a sim/tycoon needs engine component: a [Property] list of need definitions (name, decay rate/s, critical threshold, weight) with per-need 0..100 values that decay over Time.Delta, Satisfy(name, amount) to restore, an aggregate Happiness (weighted mean, [Sync(FromHost)] when networked), and static OnNeedCritical (edge-triggered: fires once crossing below threshold, re-arms above) + OnHappinessChanged (>0.25-point moves) events. Returns {created, path, className, needs[], propertyNames[], note}. Next: trigger_hotload, get_compile_errors, then attach via targetId re-call or add_component_with_properties; drive from game code (e.g. a create_interactable that calls Satisfy). Limits: per-need values live on the simulating machine only (host) — sync per-need UI yourself via RPCs; events fire on the simulating machine only; networked default true means a no-session solo playtest won. It is categorised as a Write tool in the Sbox 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_needs_system? +

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

What risk level is create_needs_system? +

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

Can I rate-limit create_needs_system? +

Yes. Add a rate_limit block to the create_needs_system 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_needs_system completely? +

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

create_needs_system is provided by the Sbox MCP server (sbox-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on Sbox, and thousands of servers like it.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Sbox's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.