AI agents invoke stop_recording 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.
While not directly destructive to data (recordings in progress are not deleted), this tool executes an operation that affects OBS Studio's state and can interrupt active recording workflows. The context shows this server controls recording, streaming, audio, and scene management—all operational state changes.
From the tool's definition The tool 'stop_recording' performs an action that triggers external operations—it controls OBS Studio's recording state via the obs-websocket plugin. Stopping a recording is an immediate action with side effects on the streaming/recording system.
Attacks that exploit this kind of access
Stop OBS recording. 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 stop_recording: 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.
stop_recording 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 stop_recording 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 stop_recording. 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.
stop_recording 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 →