AI agents invoke set_scene to trigger actions in Obs. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an external operation in OBS Studio by switching the active scene. It's not simply reading data, nor is it creating/modifying stored data in a reversible write sense — it's executing a live state change in a running application. Misuse could disrupt live streams or recordings by switching to an unintended scene, hence medium severity.
From the tool's definition "Switch OBS to a different scene" — triggers an external operation in OBS Studio, changing the active scene state
Attacks that exploit this kind of access
Switch OBS to a different scene. It is categorised as a Execute tool in the Obs MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Obs MCP server in PolicyLayer and add a rule for set_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.
set_scene is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the set_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 set_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.
set_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 →