shell_kill_job

Kill a running background shell job (useful for stuck commands).

SERVERHercules MCP SOURCE0xmihirk/hercules-mcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/0xmihirk-hercules-mcp/shell-kill-job.md

WHAT IT DOES

What shell_kill_job does on Hercules MCP

AI agents invoke shell_kill_job to trigger actions in Hercules MCP. 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.

RISK

Why shell_kill_job is rated High

This tool executes a command to kill a process, which is an Execute action—it runs system-level operations with side effects that depend on arguments (the job identifier). While not destructive in the sense of permanent data loss, killing jobs in an offensive security context could disrupt attack chains, crash tools, or terminate security testing workflows.

From the tool's definition Tool name 'shell_kill_job' and description 'Kill a running background shell job' indicate execution of system commands that terminate processes.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs shell_kill_job safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Hercules MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For shell_kill_job, this is the rule to start with:

shell_kill_job Rate-limited

shell_kill_job 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": {
    "shell_kill_job": {
      "limits": [
        {
          "counter": "shell_kill_job_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Hercules MCP, apply this rule, and every shell_kill_job call is checked against it from then on.

FAQ

Questions about shell_kill_job

What does the shell_kill_job tool do? +

Kill a running background shell job (useful for stuck commands). It is categorised as a Execute tool in the Hercules MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on shell_kill_job? +

Register the Hercules MCP server in PolicyLayer and add a rule for shell_kill_job: 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 Hercules MCP. Nothing to install.

What risk level is shell_kill_job? +

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

Can I rate-limit shell_kill_job? +

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

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

shell_kill_job is provided by the Hercules MCP server (0xmihirk/hercules-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Hercules, and thousands of servers like it.

This server

All 45 Hercules tools → High-risk tools on this server →

Across the catalogue

adb_shell_command on Android Forensics ADB MCP Server → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →