remote_bash · Mcp Remote Agent MCP: Risk & Policy

WHAT IT DOES

What remote_bash does on Mcp Remote Agent

AI agents invoke remote_bash to trigger actions in Mcp Remote Agent. 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 remote_bash needs a policy

This tool allows executing arbitrary bash commands on remote Linux servers, which is a classic Execute category risk. The severity is critical because bash command execution can be leveraged to read sensitive files, modify system configurations, install malware, pivot to other systems, or cause widespread damage depending on the permissions of the remote user.

From the tool's definition Tool name 'remote_bash' and description 'Execute bash command on remote Linux host' explicitly indicate execution of arbitrary bash commands on remote systems.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

remote_bash Rate-limited

remote_bash 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": {
    "remote_bash": {
      "limits": [
        {
          "counter": "remote_bash_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 Remote Agent, so you can run agents against it safely.

FAQ

Questions about remote_bash

What does the remote_bash tool do? +

Execute bash command on remote Linux host. Commands with special chars ($. It is categorised as a Execute tool in the Mcp Remote Agent MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on remote_bash? +

Register the Mcp Remote Agent MCP server in PolicyLayer and add a rule for remote_bash: 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 Remote Agent. Nothing to install.

What risk level is remote_bash? +

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

Can I rate-limit remote_bash? +

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

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

remote_bash is provided by the Mcp Remote Agent MCP server (knownothing20/agentport). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.