Kill a background process by name
AI agents invoke kill_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 executes system-level process termination commands. While not permanently destructive to data, killing processes can disrupt operations, cause data loss in unsaved work, interrupt services, and impact system stability. The blast radius is significant if an AI agent misuses this tool by terminating critical system or application processes.
From the tool's definition Kill a background process by name - terminates running processes which are external operations with effects that depend on the specified process name argument
Documented attack patterns abuse exactly the kind of access kill_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 kill_background:
{
"version": "1",
"default": "deny",
"tools": {
"kill_background": {
"limits": [
{
"counter": "kill_background_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}kill_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.
Kill a background process by name. 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 kill_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.
kill_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 kill_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 kill_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.
kill_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.