AI agents use create_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.
Creating a new profile is a reversible modification operation. Profiles in OBS are configuration collections that can be deleted or modified later, so this falls into the Write category rather than Destructive. The severity is medium because misuse could clutter the OBS configuration or create unwanted profiles, but the impact is limited in scope and easily reversible.
From the tool's definition Tool name: create_profile. Description: Create a new OBS profile. This creates (not retrieves) a new profile configuration in OBS Studio.
Attacks that exploit this kind of access
Create a new OBS profile. 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_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.
create_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 create_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 create_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.
create_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 →