run_bash · Friday MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_bash does on Friday MCP Server

AI agents invoke run_bash to trigger actions in Friday MCP 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 run_bash needs a policy

This tool allows execution of arbitrary bash commands, which can trigger external operations, modify system state, and access/exfiltrate sensitive data depending on command arguments. The blast radius is high if misused by an AI agent—commands could delete files, install malware, exfiltrate secrets, or pivot to other systems.

From the tool's definition Tool explicitly described as 'Run a bash command within the workspace root', enabling arbitrary command execution in a workspace environment.

Risk signalsAdmin/system-level operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_bash Rate-limited

run_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": {
    "run_bash": {
      "limits": [
        {
          "counter": "run_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 Friday MCP Server, so you can run agents against it safely.

FAQ

Questions about run_bash

What does the run_bash tool do? +

Run a bash command within the workspace root. It is categorised as a Execute tool in the Friday MCP 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 run_bash? +

Register the Friday MCP Server MCP server in PolicyLayer and add a rule for run_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 Friday MCP Server. Nothing to install.

What risk level is run_bash? +

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

Can I rate-limit run_bash? +

Yes. Add a rate_limit block to the run_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 run_bash completely? +

Set action: deny in the PolicyLayer policy for run_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 run_bash? +

run_bash is provided by the Friday MCP Server MCP server (jeremylakeyjr/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.