Run a command in background
AI agents invoke run_background to trigger actions in Bash. 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.
This tool can execute any shell command in the background without user confirmation. An AI agent with access could run malicious commands, exfiltrate data, modify system state, establish persistence, or launch further attacks. The lack of permission prompts and ability to spawn background processes multiplies the risk.
From the tool's definition 'Enables executing shell commands without permission prompts' and tool 'Run a command in background' - executes arbitrary shell commands with no safety gates
Documented attack patterns abuse exactly the kind of access run_background gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Bash, and nothing reaches the server without passing your rules. This is the rule we recommend for run_background:
{
"version": "1",
"default": "deny",
"tools": {
"run_background": {
"limits": [
{
"counter": "run_background_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_background 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.
Free to start. No card required.
Run a command in background. It is categorised as a Execute tool in the Bash MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Bash MCP server in PolicyLayer and add a rule for run_background: 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 Bash. Nothing to install.
run_background is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_background 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.
Set action: deny in the PolicyLayer policy for run_background. 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.
run_background is provided by the Bash MCP server (tinywind/bash-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Bash, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Bash tools catalogued and risk-classified — across an index of 43,000+ MCP servers.