AI agents use rename_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.
Renaming a scene modifies scene metadata but does not delete data or trigger external operations beyond OBS Studio's internal state changes. It is reversible (can be renamed again), making it Write rather than Destructive. The blast radius is medium because renaming scenes could break references in streaming/recording workflows if done maliciously, but the action is non-destructive and localized to OBS configuration.
From the tool's definition Tool name 'rename_scene' and description 'Rename an existing scene' indicate modification of existing data (scene metadata) in OBS Studio. This is a reversible change that alters configuration state.
Attacks that exploit this kind of access
Rename an existing scene. 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 rename_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.
rename_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 rename_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 rename_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.
rename_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 →