run_team · Red Team MCP: Risk & Policy

WHAT IT DOES

What run_team does on Red Team MCP

AI agents invoke run_team to trigger actions in Red Team MCP. 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 run_team needs a policy

This tool triggers execution of multiple AI agents performing tasks in coordination. While not directly destructive, write, or financial in isolation, it executes external operations (agent task runs) whose actual effects cannot be predicted without knowing the team composition and task parameters.

From the tool's definition Tool name 'run_team' combined with description 'Run a task using a predefined team of agents' indicates execution of external operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_team Rate-limited

run_team 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": {
    "run_team": {
      "limits": [
        {
          "counter": "run_team_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 Red Team MCP, so you can run agents against it safely.

FAQ

Questions about run_team

What does the run_team tool do? +

Run a task using a predefined team of agents. Easiest way to use multiple agents together. It is categorised as a Execute tool in the Red Team MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_team? +

Register the Red Team MCP server in PolicyLayer and add a rule for run_team: 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 Red Team MCP. Nothing to install.

What risk level is run_team? +

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

Can I rate-limit run_team? +

Yes. Add a rate_limit block to the run_team 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 run_team completely? +

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

run_team is provided by the Red Team MCP server (redteammcp/redteam-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.