toolmux_call · Mcp Toolmux MCP: Risk & Policy

WHAT IT DOES

What toolmux_call does on Mcp Toolmux

AI agents invoke toolmux_call to trigger actions in Mcp Toolmux. 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 toolmux_call needs a policy

This tool can execute any downstream MCP tool, meaning its effective capabilities are unbounded — it could trigger Read, Write, Execute, Destructive, or Financial actions depending on which downstream tool is called. Since it proxies arbitrary tool calls, the worst-case blast radius is critical.

From the tool's definition 'Call one downstream MCP tool through the ToolMux proxy' — this tool acts as a proxy executor that can invoke any downstream MCP tool arbitrarily.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

toolmux_call Rate-limited

toolmux_call 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": {
    "toolmux_call": {
      "limits": [
        {
          "counter": "toolmux_call_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 Toolmux, so you can run agents against it safely.

FAQ

Questions about toolmux_call

What does the toolmux_call tool do? +

Call one downstream MCP tool through the ToolMux proxy. It is categorised as a Execute tool in the Mcp Toolmux MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on toolmux_call? +

Register the Mcp Toolmux MCP server in PolicyLayer and add a rule for toolmux_call: 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 Toolmux. Nothing to install.

What risk level is toolmux_call? +

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

Can I rate-limit toolmux_call? +

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

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

toolmux_call is provided by the Mcp Toolmux MCP server (mxz-dddd/mcp-toolmux). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.