execute-batch · Ssh MCP: Risk & Policy

WHAT IT DOES

What execute-batch does on Ssh

AI agents invoke execute-batch to trigger actions in Ssh. 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 execute-batch needs a policy

This tool triggers execution of arbitrary commands on remote systems via SSH. While the server description mentions 'command whitelisting, blacklisting, and credential isolation' as security controls, the tool itself executes code/commands whose effects depend entirely on what commands are in the batch. This is quintessentially Execute category.

From the tool's definition Tool name contains 'execute' and description explicitly states 'Execute multiple commands in sequence on connected server'. The sibling tools on this SSH MCP server include execute-command, which clearly indicates this is an execution capability.

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute-batch Rate-limited

execute-batch 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": {
    "execute-batch": {
      "limits": [
        {
          "counter": "execute-batch_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 Ssh, so you can run agents against it safely.

FAQ

Questions about execute-batch

What does the execute-batch tool do? +

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

How do I enforce a policy on execute-batch? +

Register the Ssh MCP server in PolicyLayer and add a rule for execute-batch: 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 Ssh. Nothing to install.

What risk level is execute-batch? +

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

Can I rate-limit execute-batch? +

Yes. Add a rate_limit block to the execute-batch 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 execute-batch completely? +

Set action: deny in the PolicyLayer policy for execute-batch. 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 execute-batch? +

execute-batch is provided by the Ssh MCP server (zachflint/ssh-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.