send · Opencode MCP: Risk & Policy

WHAT IT DOES

What send does on Opencode

AI agents invoke send to trigger actions in Opencode. 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 send needs a policy

This tool sends messages to remote coding environments (OpenCode instances) via SSH reverse tunnels, triggering execution of coding tasks or operations on remote machines. The effects depend on the message content — an AI agent could instruct the remote coding environment to run arbitrary code, modify files, execute shell commands, etc.

From the tool's definition Send a message to the most recent opencode session on an instance. Streams the response back in real-time. Set abort=true to stop a running task instead of sending a message.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send Rate-limited

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": {
    "send": {
      "limits": [
        {
          "counter": "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 Opencode, so you can run agents against it safely.

FAQ

Questions about send

What does the send tool do? +

Send a message to the most recent opencode session on an instance. Streams the response back in real-time. Set abort=true to stop a running task instead of sending a message. It is categorised as a Execute tool in the Opencode MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on send? +

Register the Opencode MCP server in PolicyLayer and add a rule for 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 Opencode. Nothing to install.

What risk level is send? +

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

Can I rate-limit send? +

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

Set action: deny in the PolicyLayer policy for 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 send? +

send is provided by the Opencode MCP server (klutometis/opencode-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.