a2a_task_send · Wmux MCP: Risk & Policy

WHAT IT DOES

What a2a_task_send does on Wmux

AI agents invoke a2a_task_send to trigger actions in Wmux. 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 a2a_task_send needs a policy

Sending messages between agents in this context can trigger downstream execution of code, shell commands, or browser automation tasks. Given the server's purpose (running Claude Code, Codex, Gemini CLI, browser automation), a message sent to another agent likely initiates or controls execution.

From the tool's definition Alias for send_message — operates within an A2A (agent-to-agent) task communication system on a Windows tmux alternative designed for AI agents running CLI tools and browser automation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

a2a_task_send Rate-limited

a2a_task_send 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": {
    "a2a_task_send": {
      "limits": [
        {
          "counter": "a2a_task_send_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 Wmux, so you can run agents against it safely.

FAQ

Questions about a2a_task_send

What does the a2a_task_send tool do? +

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

How do I enforce a policy on a2a_task_send? +

Register the Wmux MCP server in PolicyLayer and add a rule for a2a_task_send: 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 Wmux. Nothing to install.

What risk level is a2a_task_send? +

a2a_task_send is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit a2a_task_send? +

Yes. Add a rate_limit block to the a2a_task_send 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 a2a_task_send completely? +

Set action: deny in the PolicyLayer policy for a2a_task_send. 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 a2a_task_send? +

a2a_task_send is provided by the Wmux MCP server (openwong2kim/wmux). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

a2a_task_send is one line of Wmux's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →