render_scene

Take a screenshot of the live 3D scene via the game's MCP camera for visual analysis. Pass a roomItemId of an existing CameraObject to render from that camera. Or pass position/rotation/fov to place a new CameraObject (with placeCameraItem) and render from it. Returns the uploaded screenshot URL....

Server Portals portals-mcp
Category Read
Risk class Low
Parameters 70 required

What render_scene does on Portals

AI agents call render_scene 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.

ParameterTypeRequiredDescription
fov number Camera field of view in degrees. Omit to use default.
format string Image format for the screenshot. Defaults to jpg.
position object Camera world position. Used when placeCameraItem is true or as fallback if no roomItemId.
rotation object Camera euler rotation in degrees.
roomItemId number Room item ID of an existing CameraObject to render from. Takes priority over position/rotation/fov.
placeCameraItem boolean If true, places a persistent CameraObject room item at the specified position/rotation/fov before taking the screenshot. Requires position to be specified. The
resolutionScale string Resolution scale percentage (50%, 75%, or 100% of the screen resolution). Defaults to 75.

Parameters from the server's own tool schema.

Why render_scene needs a policy

render_scene retrieves visual information from an active game scene via a camera and returns it for analysis. There are no side effects: it does not create, modify, delete, or execute operations on game state. It is purely observational, making it a Read category tool with low severity — misuse would only result in unwanted screenshots, not harmful state changes.

From the tool's definition Tool description states 'Take a screenshot of the live 3D scene' and 'Returns the uploaded screenshot URL'. The verb 'render' and 'screenshot' indicate data retrieval and visual analysis with no modification of game state or data.

Risk signalsHigh parameter count (13 properties)

Questions about render_scene

What does the render_scene tool do? +

Take a screenshot of the live 3D scene via the game's MCP camera for visual analysis. Pass a roomItemId of an existing CameraObject to render from that camera. Or pass position/rotation/fov to place a new CameraObject (with placeCameraItem) and render from it. Returns the uploaded screenshot URL. Requires an active game connection (call connect_to_game first). Use this tool alongside get_runtime_data to visually verify displayHtml overlays, UI state, and scene changes after applying operations or triggering effectors. It is categorised as a Read tool in the Portals MCP Server, which means it retrieves data without modifying state.

What parameters does render_scene accept? +

render_scene accepts 7 parameters: fov, format, position, rotation, roomItemId, placeCameraItem, resolutionScale. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on render_scene? +

Register the Portals MCP server in PolicyLayer and add a rule for render_scene: 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.

What risk level is render_scene? +

render_scene is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit render_scene? +

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

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

render_scene 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.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.