start_streaming · Obs MCP: Risk & Policy

WHAT IT DOES

What start_streaming does on Obs

AI agents invoke start_streaming 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.

WHY IT NEEDS A POLICY

Why start_streaming needs a policy

This tool executes an external operation (streaming to a configured service) whose effects depend on OBS configuration and cannot be easily undone once live. While not destructive or financial, it is Execute-class because it runs an operation with significant real-world side effects (going live, broadcasting to an audience).

From the tool's definition Tool name 'start_streaming' and description 'Start OBS streaming' indicate execution of a streaming operation that triggers external network activity and public broadcast of media content.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_streaming Rate-limited

start_streaming stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start_streaming": {
      "limits": [
        {
          "counter": "start_streaming_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Obs, so you can run agents against it safely.

FAQ

Questions about start_streaming

What does the start_streaming tool do? +

Start OBS streaming. 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.

How do I enforce a policy on start_streaming? +

Register the Obs MCP server in PolicyLayer and add a rule for start_streaming: 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.

What risk level is start_streaming? +

start_streaming is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit start_streaming? +

Yes. Add a rate_limit block to the start_streaming 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.

How do I block start_streaming completely? +

Set action: deny in the PolicyLayer policy for start_streaming. 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.

What MCP server provides start_streaming? +

start_streaming 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.