wave_start_stream · WAVE MCP Server MCP: Risk & Policy

WHAT IT DOES

What wave_start_stream does on WAVE MCP Server

AI agents invoke wave_start_stream to trigger actions in WAVE 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.

WHY IT NEEDS A POLICY

Why wave_start_stream needs a policy

This tool executes a command that initiates a streaming operation, which is an irreversible real-time action affecting external systems. While not destructive (data is not deleted), it is more severe than a simple write operation because it activates live infrastructure and begins consuming resources/quota.

From the tool's definition Tool description states it will 'Start a stream by its ID, transitioning it to the active state' — this is an operational action that triggers external services and state changes in a live streaming infrastructure.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

wave_start_stream Rate-limited

wave_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": {
    "wave_start_stream": {
      "limits": [
        {
          "counter": "wave_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 WAVE MCP Server, so you can run agents against it safely.

FAQ

Questions about wave_start_stream

What does the wave_start_stream tool do? +

Start a stream by its ID, transitioning it to the active state. It is categorised as a Execute tool in the WAVE MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on wave_start_stream? +

Register the WAVE MCP Server MCP server in PolicyLayer and add a rule for wave_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 WAVE MCP Server. Nothing to install.

What risk level is wave_start_stream? +

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

Can I rate-limit wave_start_stream? +

Yes. Add a rate_limit block to the wave_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 wave_start_stream completely? +

Set action: deny in the PolicyLayer policy for wave_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 wave_start_stream? +

wave_start_stream is provided by the WAVE MCP Server MCP server (wave-av/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.