start_stream · Optic MCP: Risk & Policy

WHAT IT DOES

What start_stream does on OpticMCP

AI agents invoke start_stream to trigger actions in OpticMCP. 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_stream needs a policy

start_stream triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_stream Rate-limited

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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start_stream": {
      "limits": [
        {
          "counter": "start_stream_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 OpticMCP, so you can run agents against it safely.

FAQ

Questions about start_stream

What does the start_stream tool do? +

start_stream. It is categorised as a Execute tool in the OpticMCP 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_stream? +

Register the Optic 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 OpticMCP. Nothing to install.

What risk level is start_stream? +

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

Can I rate-limit start_stream? +

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.

How do I block start_stream completely? +

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.

What MCP server provides start_stream? +

start_stream is provided by the Optic MCP server (timorleiderman/opticmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.