AI agents call read_screen to retrieve information from Ibmi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays current terminal screen content without modifying data. However, severity is elevated to medium rather than low because: (1) the description is empty, reducing confidence slightly; (2) on an IBM i system, terminal screens may contain sensitive business data (financial records, personal information, system credentials); (3) an agent could extract and exfiltrate this data.
From the tool's definition Tool name 'read_screen' directly indicates data retrieval from the terminal screen. Server context shows this is for IBM i TN5250 terminal interaction.
Documented attack patterns abuse exactly the kind of access read_screen 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 read_screen:
{
"version": "1",
"default": "deny",
"tools": {
"read_screen": {}
}
}read_screen is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
read_screen. It is categorised as a Read tool in the Ibmi MCP Server, which means it retrieves data without modifying state.
Register the Ibmi MCP server in PolicyLayer and add a rule for read_screen: 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.
read_screen is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the read_screen 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 read_screen. 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.
read_screen 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.