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

WHAT IT DOES

What run_crm_agent does on MCP Multi-Agent Server

AI agents invoke run_crm_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_crm_agent needs a policy

The tool executes agent operations with unspecified scope. While it could theoretically perform reads, the presence of destructive siblings (delete_company_document) and financial operations (create_salesforce_lead) on the same server suggests run_crm_agent could trigger any CRM workflow.

From the tool's definition Tool description states "CRM Agent에게 직접 작업을 요청합니다" (Request tasks directly to CRM Agent). Combined with sibling tools including create_salesforce_lead, delete_company_document, and delete_calendar_event, this tool delegates arbitrary work to a CRM agent whose…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_crm_agent Rate-limited

run_crm_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_crm_agent": {
      "limits": [
        {
          "counter": "run_crm_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_crm_agent

What does the run_crm_agent tool do? +

CRM 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_crm_agent? +

Register the MCP Multi-Agent Server MCP server in PolicyLayer and add a rule for run_crm_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_crm_agent? +

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

Can I rate-limit run_crm_agent? +

Yes. Add a rate_limit block to the run_crm_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_crm_agent completely? +

Set action: deny in the PolicyLayer policy for run_crm_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_crm_agent? +

run_crm_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.