Create a compact, capability-grounded implementation contract for a Portals gameplay mechanic. This does not edit the room. It returns required capabilities, objects, variables, triggers, actions, validation steps, risks, and sources.
AI agents call plan_gameplay_mechanic to retrieve information from Portals without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
mechanic | string | Yes | Gameplay mechanic to plan, for example: locked door, lap counter, stealth detection. |
constraints | array | — | Optional constraints such as multiplayer, persistent state, no custom assets, or selected item IDs. |
max_results | integer | — | Maximum grounding matches to include (default: 5). |
Parameters from the server's own tool schema.
The tool explicitly states it does not edit the room and only returns a plan/contract. It is purely a read/query operation that produces a structured output without any side effects.
From the tool's definition 'This does not edit the room. It returns required capabilities, objects, variables, triggers, actions, validation steps, risks, and sources.'
Attacks that exploit this kind of access
Create a compact, capability-grounded implementation contract for a Portals gameplay mechanic. This does not edit the room. It returns required capabilities, objects, variables, triggers, actions, validation steps, risks, and sources. It is categorised as a Read tool in the Portals MCP Server, which means it retrieves data without modifying state.
plan_gameplay_mechanic accepts 3 parameters: mechanic, constraints, max_results. Required: mechanic. The full parameter table on this page comes from the server's own tool schema.
Register the Portals MCP server in PolicyLayer and add a rule for plan_gameplay_mechanic: 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 Portals. Nothing to install.
plan_gameplay_mechanic is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the plan_gameplay_mechanic 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.
Set action: deny in the PolicyLayer policy for plan_gameplay_mechanic. 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.
plan_gameplay_mechanic is provided by the Portals MCP server (portals-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →