exec_mcp_tool · MCP Router MCP: Risk & Policy

WHAT IT DOES

What exec_mcp_tool does on MCP Router

AI agents invoke exec_mcp_tool to trigger actions in MCP Router. 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 exec_mcp_tool needs a policy

This tool runs arbitrary tools on remote MCP servers. The effects are determined by which tool is executed and its arguments, making outcomes unpredictable. The tool acts as a proxy for executing any registered tool, potentially with side effects ranging from read operations to destructive actions.

From the tool's definition Tool description explicitly states 'Execute a tool on a target MCP server.' The name 'exec_mcp_tool' and verb 'Execute' directly indicate code/command execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

exec_mcp_tool Rate-limited

exec_mcp_tool 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": {
    "exec_mcp_tool": {
      "limits": [
        {
          "counter": "exec_mcp_tool_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 Router, so you can run agents against it safely.

FAQ

Questions about exec_mcp_tool

What does the exec_mcp_tool tool do? +

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

How do I enforce a policy on exec_mcp_tool? +

Register the MCP Router MCP server in PolicyLayer and add a rule for exec_mcp_tool: 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 Router. Nothing to install.

What risk level is exec_mcp_tool? +

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

Can I rate-limit exec_mcp_tool? +

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

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

exec_mcp_tool is provided by the MCP Router MCP server (maverick-ljxuan/mcp-router). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.