Reads text output from a terminal session. Returns the current screen contents. Use mcpretentious-screenshot for rich terminal info including colors, cursor position, and styles.
AI agents call mcpretentious-read to retrieve information from MCPretentious without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves terminal session data without side effects. It queries the current state of a terminal screen. Although the broader server enables Execute-class operations (keyboard input, mouse control), this specific tool performs only information retrieval. The tool's name 'mcpretentious-read' and explicit read-only behavior in the description confirm it belongs in the Read category.
From the tool's definition Tool description states it 'Reads text output from a terminal session' and 'Returns the current screen contents.' The function is explicitly read-only with no capability to modify, execute, or delete data.
Documented attack patterns abuse exactly the kind of access mcpretentious-read gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCPretentious, and nothing reaches the server without passing your rules. This is the rule we recommend for mcpretentious-read:
{
"version": "1",
"default": "deny",
"tools": {
"mcpretentious-read": {}
}
}mcpretentious-read 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.
Reads text output from a terminal session. Returns the current screen contents. Use mcpretentious-screenshot for rich terminal info including colors, cursor position, and styles. It is categorised as a Read tool in the MCPretentious MCP Server, which means it retrieves data without modifying state.
Register the MCPretentious MCP server in PolicyLayer and add a rule for mcpretentious-read: 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 MCPretentious. Nothing to install.
mcpretentious-read 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 mcpretentious-read 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 mcpretentious-read. 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.
mcpretentious-read is provided by the MCPretentious MCP server (oetiker/mcpretentious). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCPretentious, 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.
9 MCPretentious tools catalogued and risk-classified — across an index of 43,000+ MCP servers.