crewai_replay_task · CrewAI MCP Orchestrator MCP

WHAT IT DOES

What crewai_replay_task does on CrewAI MCP Orchestrator

AI agents invoke crewai_replay_task to trigger actions in CrewAI MCP Orchestrator. 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 crewai_replay_task needs a policy

Based on the tool name and server context, this tool likely re-executes or replays a previously run CrewAI task. Given the server is an orchestrator for multi-agent systems, replaying a task would trigger execution of agent workflows, which falls under Execute. Severity is high because re-running agent tasks could have significant side effects depending on what the agents do.

From the tool's definition Tool name: crewai_replay_task — no description provided

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

crewai_replay_task Rate-limited

crewai_replay_task 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": {
    "crewai_replay_task": {
      "limits": [
        {
          "counter": "crewai_replay_task_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 CrewAI MCP Orchestrator, so you can run agents against it safely.

FAQ

Questions about crewai_replay_task

What does the crewai_replay_task tool do? +

crewai_replay_task. It is categorised as a Execute tool in the CrewAI MCP Orchestrator MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on crewai_replay_task? +

Register the CrewAI MCP Orchestrator MCP server in PolicyLayer and add a rule for crewai_replay_task: 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 CrewAI MCP Orchestrator. Nothing to install.

What risk level is crewai_replay_task? +

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

Can I rate-limit crewai_replay_task? +

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

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

crewai_replay_task is provided by the CrewAI MCP Orchestrator MCP server (ssolis-ti/crewai-mcp-hq). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.