Terminal Reader

Provides read-only access to terminal outputs captured via cap for Claude Desktop

javascript

0

GitHub Stars

javascript

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "chrisvin-jabamani-terminal-reader-mcp": {
      "command": "node",
      "args": [
        "/FULL/PATH/TO/terminal-reader-mcp/index.js"
      ]
    }
  }
}

You set up a small MCP server that lets Claude Desktop read your terminal output in a controlled, read-only way. You capture terminal activity with a simple cap function, point Claude at the local MCP server, and then ask Claude questions about your recent commands and outputs. This makes reviewing terminal history fast and error-free without copy-pasting.

How to use

Use the cap function to feed Claude your terminal activity. Prefix commands with cap so Claude can see both the commands you run and their outputs. Then ask Claude questions like what was my last terminal command or what happened in the latest execution.

Example workflows you can perform:

Only commands prefixed with cap are captured. Commands run without cap are not included in Claude’s view.

Example quickstart flow

# Start by preparing your environment
# (Follow these steps exactly in your shell)

The cap function and Claude configuration steps are shown separately in the setup flow below.

Available tools

cap

Shell function to capture terminal commands and their outputs to a log file for Claude to read.