start_live · TikVid MCP Server MCP: Risk & Policy

WHAT IT DOES

What start_live does on TikVid MCP Server

AI agents invoke start_live to trigger actions in TikVid 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 start_live needs a policy

start_live executes an operational command that initiates a live broadcast and notification system. While not destructive or financial, it triggers external actions and state changes (stream goes live, notifications sent) that represent real-world effects.

From the tool's definition Tool performs 'Start a live stream' with side effects: it triggers a broadcast action and initiates notifications to followers ('Followers get notified'). This is an external operation whose effects depend on execution, not a data read or reversible write.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_live Rate-limited

start_live 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_live": {
      "limits": [
        {
          "counter": "start_live_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 TikVid MCP Server, so you can run agents against it safely.

FAQ

Questions about start_live

What does the start_live tool do? +

Start a live stream on TikVid. Followers get notified. It is categorised as a Execute tool in the TikVid 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 start_live? +

Register the TikVid MCP Server MCP server in PolicyLayer and add a rule for start_live: 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 TikVid MCP Server. Nothing to install.

What risk level is start_live? +

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

Can I rate-limit start_live? +

Yes. Add a rate_limit block to the start_live 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_live completely? +

Set action: deny in the PolicyLayer policy for start_live. 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_live? +

start_live is provided by the TikVid MCP Server MCP server (liortesta/tikvid). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.