Position the cursor at the specified location.
AI agents invoke set_cursor 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.
Setting the cursor position on a 5250 green-screen terminal is an interactive terminal operation that changes the state of the session. While it doesn't directly read or write data, it triggers an external operation on the IBM i system's terminal interface.
From the tool's definition 'Position the cursor at the specified location' on a TN5250 terminal session — this is a terminal interaction action that manipulates the state of an active terminal session
Documented attack patterns abuse exactly the kind of access set_cursor 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 set_cursor:
{
"version": "1",
"default": "deny",
"tools": {
"set_cursor": {
"limits": [
{
"counter": "set_cursor_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}set_cursor 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.
Position the cursor at the specified location. 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 set_cursor: 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.
set_cursor 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 set_cursor 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 set_cursor. 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.
set_cursor 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.