Read a rectangular region of the terminal buffer as text.
AI agents call read_region to retrieve information from Tui without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves terminal buffer content without modifying, executing, or deleting anything. It is a non-destructive query operation that only accesses and returns existing data from the terminal interface. There is no capability to execute commands, modify state, or cause irreversible changes.
From the tool's definition Tool name is 'read_region' and description states 'Read a rectangular region of the terminal buffer as text.' The verb 'read' and the explicit statement that it reads/retrieves text content indicate pure data retrieval with no side effects.
Documented attack patterns abuse exactly the kind of access read_region gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tui, and nothing reaches the server without passing your rules. This is the rule we recommend for read_region:
{
"version": "1",
"default": "deny",
"tools": {
"read_region": {}
}
}read_region 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 a rectangular region of the terminal buffer as text. It is categorised as a Read tool in the Tui MCP Server, which means it retrieves data without modifying state.
Register the Tui MCP server in PolicyLayer and add a rule for read_region: 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 Tui. Nothing to install.
read_region 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_region 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_region. 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_region is provided by the Tui MCP server (nvms/tui-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Tui, 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.
13 Tui tools catalogued and risk-classified — across an index of 43,000+ MCP servers.