Send an attention/function key and wait for the host response.
AI agents invoke send_key to trigger actions in Ibmi. 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.
Sending function/attention keys to an IBM i green-screen terminal can trigger arbitrary host-side execution: submitting jobs, running commands, confirming destructive operations, navigating menus, etc. The effect depends entirely on the current screen state and which key is sent (e.g., Enter, F3, F12, PF keys that submit jobs).
From the tool's definition 'Send an attention/function key and wait for the host response' — sends keystrokes to an active IBM i 5250 terminal session, triggering host-side operations
Documented attack patterns abuse exactly the kind of access send_key gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ibmi, and nothing reaches the server without passing your rules. This is the rule we recommend for send_key:
{
"version": "1",
"default": "deny",
"tools": {
"send_key": {
"limits": [
{
"counter": "send_key_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}send_key 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.
Send an attention/function key and wait for the host response. It is categorised as a Execute tool in the Ibmi MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ibmi MCP server in PolicyLayer and add a rule for send_key: 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 Ibmi. Nothing to install.
send_key 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 send_key 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 send_key. 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.
send_key is provided by the Ibmi MCP server (whitehornltd/ibmi-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ibmi, 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.
8 Ibmi tools catalogued and risk-classified — across an index of 43,000+ MCP servers.