AI agents use set_canvas_resolution 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 modifies OBS Studio's global canvas and output resolution settings, affecting all scenes in the current collection. It is a Write operation (reversible configuration change), but carries high severity because the change is global and can disrupt all active scenes, recordings, or streams simultaneously if misused.
From the tool's definition 'Set the OBS canvas (base) and output resolution. Applies globally — affects all scenes in the current collection.'
Attacks that exploit this kind of access
Set the OBS canvas (base) and output resolution. Applies globally — affects all scenes in the current collection. 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_canvas_resolution: 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_canvas_resolution 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_canvas_resolution 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_canvas_resolution. 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_canvas_resolution 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 →