@mcp-use/cli 1.0.0

package/package.json

@@ -0,0 +1,82 @@
+{
+	"name": "@mcp-use/cli",
+	"version": "1.0.0",
+	"license": "MIT",
+	"description": "A CLI tool for interacting with Model Context Protocol (MCP) servers using natural language",
+	"keywords": [
+		"mcp",
+		"model-context-protocol",
+		"cli",
+		"ai",
+		"langchain",
+		"openai"
+	],
+	"author": "Pietro",
+	"repository": {
+		"type": "git",
+		"url": "https://github.com/your-username/mcp-use-cli"
+	},
+	"bin": {
+		"mcp-use": "dist/cli.js"
+	},
+	"type": "module",
+	"engines": {
+		"node": ">=16"
+	},
+	"scripts": {
+		"build": "tsc",
+		"dev": "tsc --watch",
+		"test": "prettier --check . && xo && ava"
+	},
+	"files": [
+		"dist"
+	],
+	"dependencies": {
+		"@hey-api/client-fetch": "^0.12.0",
+		"@langchain/anthropic": "^0.3.23",
+		"@langchain/core": "^0.3.60",
+		"@langchain/google-genai": "^0.2.13",
+		"@langchain/mistralai": "^0.2.1",
+		"@langchain/openai": "^0.5.14",
+		"dotenv": "^16.5.0",
+		"ink": "^5.2.1",
+		"ink-big-text": "^2.0.0",
+		"ink-text-input": "^6.0.0",
+		"mcp-use": "^0.0.8",
+		"meow": "^11.0.0",
+		"react": "^18.2.0",
+		"zod": "^3.25.56"
+	},
+	"devDependencies": {
+		"@sindresorhus/tsconfig": "^3.0.1",
+		"@types/react": "^18.0.32",
+		"@vdemedes/prettier-config": "^2.0.1",
+		"ava": "^5.2.0",
+		"chalk": "^5.2.0",
+		"eslint-config-xo-react": "^0.27.0",
+		"eslint-plugin-react": "^7.32.2",
+		"eslint-plugin-react-hooks": "^4.6.0",
+		"ink-testing-library": "^3.0.0",
+		"prettier": "^2.8.7",
+		"ts-node": "^10.9.1",
+		"typescript": "^5.0.3",
+		"xo": "^0.53.1"
+	},
+	"ava": {
+		"extensions": {
+			"ts": "module",
+			"tsx": "module"
+		},
+		"nodeArguments": [
+			"--loader=ts-node/esm"
+		]
+	},
+	"xo": {
+		"extends": "xo-react",
+		"prettier": true,
+		"rules": {
+			"react/prop-types": "off"
+		}
+	},
+	"prettier": "@vdemedes/prettier-config"
+}

package/readme.md

@@ -0,0 +1,154 @@
+<div align="center">
+  <img src="static/terminal.png" alt="Terminal" />
+</div>
+
+A CLI tool for interacting with Model Context Protocol (MCP) servers using natural language. Built with [mcp-use](https://github.com/mcp-use/mcp-use-ts) and powered by OpenAI's GPT models.
+
+## Features
+
+- 🤖 Natural language interface for MCP servers
+- 🔧 Built-in filesystem MCP server support
+- 💬 Interactive chat interface with tool call visualization
+- ⚡ Direct integration with mcp-use (no API layer needed)
+- 🚀 Single command installation
+- 🔄 **Multiple LLM providers** (OpenAI, Anthropic, Google, Mistral)
+- ⚙️ **Slash commands** for configuration (like Claude Code)
+- 🔑 **Smart API key prompting** - automatically asks for keys when needed
+- 💾 **Persistent secure storage** - encrypted keys and settings saved across sessions
+
+## Install
+
+```bash
+$ npm install --global mcp-use-cli
+```
+
+## Quick Start
+
+1. **Install and run**:
+   ```bash
+   $ npm install --global mcp-use-cli
+   $ mcp-use-cli
+   ```
+
+2. **Choose your model** (CLI handles API key setup automatically):
+   ```bash
+   # Just pick a model - that's it!
+   /model openai gpt-4o-mini
+   /model anthropic claude-3-5-sonnet-20241022
+   /model google gemini-1.5-pro
+   
+   # CLI will prompt: "Please enter your OPENAI API key:"
+   # Paste your key and start chatting immediately!
+   ```
+
+3. **Get API keys** when prompted from:
+   - [OpenAI](https://platform.openai.com/api-keys)
+   - [Anthropic](https://console.anthropic.com/) 
+   - [Google AI](https://aistudio.google.com/app/apikey)
+   - [Mistral](https://console.mistral.ai/)
+
+> **Keys are stored securely encrypted** in `~/.mcp-use-cli/config.json` and persist across sessions.
+
+## Alternative Setup
+
+If you prefer environment variables:
+```bash
+export OPENAI_API_KEY=your_key_here
+export ANTHROPIC_API_KEY=your_key_here
+# Then just run: mcp-use-cli
+```
+
+## Usage
+
+```
+$ mcp-use-cli --help
+
+  Usage
+    $ mcp-use-cli
+
+  Options
+    --name        Your name (optional)
+    --config      Path to MCP configuration file (optional)
+
+  Examples
+    $ mcp-use-cli
+    $ mcp-use-cli --name=Jane
+    $ mcp-use-cli --config=./mcp-config.json
+
+  Environment Variables
+    OPENAI_API_KEY    Required - Your OpenAI API key
+
+  Setup
+    1. Set your OpenAI API key: export OPENAI_API_KEY=your_key_here
+    2. Run: mcp-use-cli
+    3. Start chatting with MCP servers!
+```
+
+## Configuration
+
+By default, the CLI connects to a filesystem MCP server in `/tmp`. You can provide a custom configuration file:
+
+```json
+{
+  "servers": {
+    "filesystem": {
+      "command": "npx",
+      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/directory"],
+      "env": {}
+    },
+    "other-server": {
+      "command": "your-mcp-server-command",
+      "args": ["--arg1", "value1"],
+      "env": {}
+    }
+  }
+}
+```
+
+## Slash Commands
+
+Switch LLM providers and configure settings using slash commands (similar to Claude Code):
+
+```bash
+# Set API keys (stored securely)
+/setkey openai sk-1234567890abcdef...
+/setkey anthropic ant_1234567890abcdef...
+/clearkeys  # Clear all stored keys
+
+# Switch models
+/model openai gpt-4o
+/model anthropic claude-3-5-sonnet-20241022
+/model google gemini-1.5-pro
+/model mistral mistral-large-latest
+
+# List available models
+/models
+/models anthropic
+
+# Configuration
+/config temp 0.5
+/config tokens 4000
+
+# Status and help
+/status
+/help
+```
+
+## Chat Examples
+
+- "List files in the current directory"
+- "Create a new file called hello.txt with the content 'Hello, World!'"
+- "Search for files containing 'TODO'"
+- "What's the structure of this project?"
+
+## Architecture
+
+This CLI uses:
+- **Frontend**: React + Ink for the terminal UI
+- **Agent**: mcp-use MCPAgent for LLM + MCP integration
+- **LLM**: OpenAI GPT-4o-mini
+- **Transport**: Direct TypeScript integration (no API layer)
+
+## License
+
+MIT