aider_run_command · Aider MCP WebSocket Server MCP

WHAT IT DOES

What aider_run_command does on Aider MCP WebSocket Server

AI agents invoke aider_run_command to trigger actions in Aider MCP WebSocket Server. 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 aider_run_command needs a policy

Running shell commands is a quintessential Execute category action, as the effects depend entirely on the command arguments provided by the AI agent. With shell access, an agent could read sensitive files, modify system state, exfiltrate data, or cause denial of service.

From the tool's definition Tool name 'aider_run_command' and description 'Run a shell command via Aider' explicitly indicate execution of arbitrary shell commands.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

aider_run_command Rate-limited

aider_run_command 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": {
    "aider_run_command": {
      "limits": [
        {
          "counter": "aider_run_command_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 Aider MCP WebSocket Server, so you can run agents against it safely.

FAQ

Questions about aider_run_command

What does the aider_run_command tool do? +

Run a shell command via Aider. It is categorised as a Execute tool in the Aider MCP WebSocket Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on aider_run_command? +

Register the Aider MCP WebSocket Server MCP server in PolicyLayer and add a rule for aider_run_command: 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 Aider MCP WebSocket Server. Nothing to install.

What risk level is aider_run_command? +

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

Can I rate-limit aider_run_command? +

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

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

aider_run_command is provided by the Aider MCP WebSocket Server MCP server (larock22/aider-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.