AI agents invoke obs-stop-stream to trigger actions in OBS MCP Server. 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.
This tool stops an active stream, which is an external operation with real-world consequences (interrupting live broadcast to audiences). It is not a read operation (no data retrieval), not write (not creating/modifying persistent data reversibly), not destructive (the stream can be restarted), and not financial (no money movement). It fits Execute because it runs a command whose effects depend on application state.
From the tool's definition Tool name 'obs-stop-stream' and description 'Stop streaming in OBS' indicate an action that triggers an external operation (halting an active broadcast stream) with effects that depend on the state of the OBS application.
Documented attack patterns abuse exactly the kind of access obs-stop-stream gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OBS MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for obs-stop-stream:
{
"version": "1",
"default": "deny",
"tools": {
"obs-stop-stream": {
"limits": [
{
"counter": "obs-stop-stream_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} obs-stop-stream 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.
Free to start. No card required.
Stop streaming in OBS. It is categorised as a Execute tool in the OBS MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OBS MCP Server MCP server in PolicyLayer and add a rule for obs-stop-stream: 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 MCP Server. Nothing to install.
obs-stop-stream 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 obs-stop-stream 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 obs-stop-stream. 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.
obs-stop-stream is provided by the OBS MCP Server MCP server (royshil/obs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 200 OBS MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
200 OBS MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.