AI agents use set_profile 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 performs a reversible state change (switching profiles) rather than executing arbitrary operations or irreversibly destroying data. The impact is medium severity because a misconfigured profile switch could disrupt ongoing streams or recordings, but the change is easily reverted by switching back to the previous profile.
From the tool's definition Tool description states 'Switch to a different OBS profile (stream settings, encoder config, etc.)' - this modifies active configuration state in OBS Studio by selecting a different profile, which affects how streaming and recording will behave.
Attacks that exploit this kind of access
Switch to a different OBS profile (stream settings, encoder config, etc.). 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 set_profile: 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_profile 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 set_profile 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_profile. 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_profile 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 →