run_report_agent · MCP Multi-Agent Server MCP: Risk & Policy

WHAT IT DOES

What run_report_agent does on MCP Multi-Agent Server

AI agents invoke run_report_agent to trigger actions in MCP Multi-Agent 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 run_report_agent needs a policy

This tool invokes a specialized agent to perform unspecified work. Since the description does not detail what constraints exist on the Report Agent's capabilities, and given the multi-domain nature of the system with peers capable of destructive and financial operations, this represents an Execute-level risk—arbitrary work requests to an autonomous agent that can trigger side effects depending on the request…

From the tool's definition Tool description states 'Report Agent에게 직접 작업을 요청합니다' (request work directly from Report Agent). The ability to request arbitrary work from a specialized agent without specified constraints, combined with the sibling tools that perform financial…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_report_agent Rate-limited

run_report_agent 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_report_agent": {
      "limits": [
        {
          "counter": "run_report_agent_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 MCP Multi-Agent Server, so you can run agents against it safely.

FAQ

Questions about run_report_agent

What does the run_report_agent tool do? +

Report Agent에게 직접 작업을 요청합니다. It is categorised as a Execute tool in the MCP Multi-Agent 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 run_report_agent? +

Register the MCP Multi-Agent Server MCP server in PolicyLayer and add a rule for run_report_agent: 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 MCP Multi-Agent Server. Nothing to install.

What risk level is run_report_agent? +

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

Can I rate-limit run_report_agent? +

Yes. Add a rate_limit block to the run_report_agent 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_report_agent completely? +

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

run_report_agent is provided by the MCP Multi-Agent Server MCP server (sunnylabtv-crypto/ai_mcp_multi_agent-public). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.