run_adhoc_command

THE RISK

High Risk

This tool executes commands on infrastructure nodes without explicit restriction on command type or scope. Ad-hoc commands in Ansible can perform any action permitted by the target hosts' permissions—including reading files, modifying configurations, installing software, or executing destructive operations.

From the tool's definition Tool name 'run_adhoc_command' combined with description 'Run an ad-hoc Ansible command against inventory hosts' indicates execution of arbitrary Ansible commands on remote systems.

Documented attack patterns abuse exactly the kind of access run_adhoc_command gives an agent:

HOW TO CONTROL RUN_ADHOC_COMMAND

PolicyLayer is an MCP gateway — it sits between your AI agents and AAP Enterprise MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for run_adhoc_command:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_adhoc_command": {
      "limits": [
        {
          "counter": "run_adhoc_command_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

run_adhoc_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.

Create a free account and register AAP Enterprise MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

More AAP Enterprise MCP Server tools

Destructive delete_activation Delete an activation. Destructive delete_host Delete a host from inventory. Destructive delete_inventory Delete an inventory from Ansible Automation Platform. Destructive delete_inventory_source Delete an inventory source. Destructive remove_host_from_group Remove a host from a group. Execute restart_activation Restart an activation. Execute run_job Run a job template by ID, optionally with extra_vars. Execute sync_inventory_source Manually trigger a sync for an inventory source.

All 69 AAP Enterprise MCP Server tools →

Execute tools on other servers

Frida Game Hacking MCP remove_breakpoint Procmon request_elevation WireMCP capture_packets Pentest Ai run_probe

Go deeper

High-risk tools in AAP Enterprise MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

What does the run_adhoc_command tool do? +

Run an ad-hoc Ansible command against inventory hosts. It is categorised as a Execute tool in the AAP Enterprise 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_adhoc_command? +

Register the AAP Enterprise MCP Server MCP server in PolicyLayer and add a rule for run_adhoc_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 AAP Enterprise MCP Server. Nothing to install.

What risk level is run_adhoc_command? +

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

Can I rate-limit run_adhoc_command? +

Yes. Add a rate_limit block to the run_adhoc_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 run_adhoc_command completely? +

Set action: deny in the PolicyLayer policy for run_adhoc_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 run_adhoc_command? +

run_adhoc_command is provided by the AAP Enterprise MCP Server MCP server (sibilleb/aap-enterprise-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every AAP Enterprise MCP Server tool call.

Deterministic rules across all 69 AAP Enterprise MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

GOVERN AAP ENTERPRISE →

Free to start. No card required.

69 AAP Enterprise MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// WHAT RUN_ADHOC_COMMAND ON AAP ENTERPRISE MCP SERVER DOES

// THE RISK

// HOW TO CONTROL RUN_ADHOC_COMMAND

// EXPLORE