AI agents use create_scene to create or update resources in Obs — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Obs environment.
This tool creates a new scene resource in OBS Studio, which is a reversible Write operation. Scenes are configuration containers with no destructive or external execution implications. The blast radius is minimal—a user can easily delete unwanted scenes. Low severity because scene creation is a normal, low-impact OBS workflow action.
From the tool's definition Tool name 'create_scene' and description 'Create a new empty scene in OBS' indicate creation of a new configuration object that is reversible (scenes can be deleted via remove_scene tool shown in sibling tools).
Attacks that exploit this kind of access
Create a new empty scene in OBS. It is categorised as a Write tool in the Obs MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Obs MCP server in PolicyLayer and add a rule for create_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 Obs. Nothing to install.
create_scene is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_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.
Set action: deny in the PolicyLayer policy for create_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.
create_scene is provided by the Obs MCP server (larscangit/obs-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 →