AI agents invoke start_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 triggers a real-time operation that initiates a broadcast stream. While not destructive or financial in itself, it executes an action whose effects are immediate and externally observable. An AI agent misusing this could start an unintended stream to an audience, causing reputational or operational harm.
From the tool's definition Tool name 'start_stream' and description 'Starts the stream output' indicate execution of a streaming operation with externally visible effects (broadcasting begins).
Documented attack patterns abuse exactly the kind of access start_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 start_stream:
{
"version": "1",
"default": "deny",
"tools": {
"start_stream": {
"limits": [
{
"counter": "start_stream_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} start_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.
Starts the stream output. 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 start_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.
start_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 start_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 start_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.
start_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.