Cognitive-Stack
diff --git a/‎.gitignore‎
Lines changed: 3 additions & 1 deletion b/‎.gitignore‎
Lines changed: 3 additions & 1 deletion
diff --git a/‎README.md‎
Lines changed: 87 additions & 4 deletions b/‎README.md‎
Lines changed: 87 additions & 4 deletions
diff --git a/‎pyproject.toml‎
Lines changed: 3 additions & 2 deletions b/‎pyproject.toml‎
Lines changed: 3 additions & 2 deletions
diff --git a/‎src/mcphub/cli/README.md‎
Lines changed: 144 additions & 0 deletions b/‎src/mcphub/cli/README.md‎
Lines changed: 144 additions & 0 deletions
@@ -48,4 +48,6 @@ __pycache__/
 .cursor/
 
 # cache dir
-.mcphub_cache/
+.mcphub_cache/
+
+.coverage
@@ -2,6 +2,13 @@
 
 MCPHub is an embeddable Model Context Protocol (MCP) solution for AI services. It enables seamless integration of MCP servers into any AI framework, allowing developers to easily configure, set up, and manage MCP servers within their applications. Whether you're using OpenAI Agents, LangChain, or Autogen, MCPHub provides a unified way to connect your AI services with MCP tools and resources.
 
+## Documentation
+
+- [CLI Documentation](src/mcphub/cli/README.md) - Command-line interface for managing MCP servers
+- [API Documentation](docs/api.md) - Python API reference
+- [Configuration Guide](docs/configuration.md) - Server configuration details
+- [Examples](docs/examples.md) - Usage examples and tutorials
+
 ## Quick Start
 
 ### Prerequisites
@@ -49,6 +56,33 @@ Create a `.mcphub.json` file in your project root:
 }
 ```
 
+### Adding New MCP Servers
+
+You can add new MCP servers in two ways:
+
+1. **Manual Configuration**: Add the server configuration directly to your `.mcphub.json` file.
+
+2. **Automatic Configuration from GitHub**: Use the `add_server_from_repo` method to automatically configure a server from its GitHub repository:
+
+```python
+from mcphub import MCPHub
+
+# Initialize MCPHub
+hub = MCPHub()
+
+# Add a new server from GitHub
+hub.servers_params.add_server_from_repo(
+    server_name="my-server",
+    repo_url="https://github.com/username/repo"
+)
+```
+
+The automatic configuration:
+- Fetches the README from the GitHub repository
+- Uses OpenAI to analyze the README and extract the server configuration
+- Adds the configuration to your `.mcphub.json` file
+- Requires an OpenAI API key (set via `OPENAI_API_KEY` environment variable)
+
 ### Usage with OpenAI Agents
 
 ```python
@@ -175,20 +209,66 @@ Configure your MCP servers in `.mcphub.json`:
 ### Transport Support
 
 - **stdio Transport**: Run MCP servers as local subprocesses
+- **SSE Transport**: Run MCP servers with Server-Sent Events (SSE) support using supergateway
 - **Automatic Path Management**: Manages server paths and working directories
 - **Environment Variable Handling**: Configurable environment variables per server
 
+#### Running Servers with SSE Support
+
+You can run MCP servers with SSE support using the `mcphub run` command:
+
+```bash
+# Basic usage with default settings
+mcphub run your-server-name --sse
+
+# Advanced usage with custom settings
+mcphub run your-server-name --sse \
+    --port 8000 \
+    --base-url http://localhost:8000 \
+    --sse-path /sse \
+    --message-path /message
+```
+
+SSE support is useful when you need to:
+- Connect to MCP servers from web applications
+- Use real-time communication with MCP servers
+- Integrate with clients that support SSE
+
+The SSE server provides two endpoints:
+- `/sse`: SSE endpoint for real-time updates
+- `/message`: HTTP endpoint for sending messages
+
+Example configuration in `.mcphub.json`:
+```json
+{
+    "mcpServers": {
+        "sequential-thinking-mcp": {
+            "package_name": "smithery-ai/server-sequential-thinking",
+            "command": "npx",
+            "args": [
+                "-y",
+                "@smithery/cli@latest",
+                "run",
+                "@smithery-ai/server-sequential-thinking",
+                "--key",
+                "your-api-key"
+            ]
+        }
+    }
+}
+```
+
 ### Framework Integration
 
 Provides adapters for popular AI frameworks:
-- OpenAI Agents
-- LangChain
-- Autogen
+- OpenAI Agents ([example](examples/with_openai.py))
+- LangChain ([example](examples/with_langchain.py))
+- Autogen ([example](examples/with_autogen.py))
 
 ```python
 from mcphub import MCPHub
 
-async def framework_examples():
+async def framework_quick_examples():
     hub = MCPHub()
 
     # 1. OpenAI Agents Integration
@@ -230,6 +310,9 @@ from mcphub import MCPHub
 async def tool_management():
     hub = MCPHub()
 
+    # List all servers
+    servers = hub.list_servers()
+
     # List all tools from a specific MCP server
     tools = await hub.list_tools(mcp_name="sequential-thinking-mcp")
 
 
@@ -21,7 +21,7 @@ classifiers = [
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
 ]
-dependencies = []
+dependencies = ["pydantic (>=2.11.4,<3.0.0)", "rich (>=14.0.0,<15.0.0)", "openai (>=1.78.0,<2.0.0)", "psutil (>=7.0.0,<8.0.0)"]
 requires-python = "<4.0,>=3.10"
 
 [project.optional-dependencies]
@@ -54,4 +54,5 @@ mcphub = "mcphub.cli.commands:main"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^8.3.5"
-pytest-asyncio = "^0.26.0"
+pytest-asyncio = "^0.26.0"
+pytest-cov = "^6.1.1"
@@ -0,0 +1,144 @@
+# MCPHub CLI
+
+The MCPHub CLI is a command-line interface tool for managing Model Context Protocol (MCP) server configurations. It provides a user-friendly way to add, remove, monitor, and run MCP servers.
+
+## Installation
+
+The CLI is included with the MCPHub package. Install it using pip:
+
+```bash
+pip install mcphub
+```
+
+## Available Commands
+
+### 1. Add a Server (`add`)
+Add a new MCP server from a GitHub repository to your local configuration.
+
+```bash
+mcphub add <repo_url> [mcp_name]
+```
+
+Options:
+- `repo_url`: GitHub repository URL of the MCP server
+- `mcp_name` (optional): Custom name for the MCP server
+- `-n, --non-interactive`: Skip environment variable prompts
+
+Example:
+```bash
+mcphub add https://github.com/username/repo my-server
+```
+
+### 2. Remove a Server (`remove`)
+Remove an MCP server configuration from your local config.
+
+```bash
+mcphub remove <mcp_name>
+```
+
+Example:
+```bash
+mcphub remove my-server
+```
+
+### 3. List Servers (`ps`)
+List all configured MCP servers with detailed process information.
+
+```bash
+mcphub ps
+```
+
+Shows:
+- Server name
+- Status (running/not running)
+- Ports
+- Command
+- Creation time
+- Uptime
+
+### 4. Check Server Status (`status`)
+Show detailed status information for a specific MCP server.
+
+```bash
+mcphub status <mcp_name>
+```
+
+Example:
+```bash
+mcphub status my-server
+```
+
+### 5. Run a Server (`run`)
+Run a configured MCP server with optional SSE support.
+
+```bash
+mcphub run <mcp_name> [options]
+```
+
+Options:
+- `--sse`: Enable Server-Sent Events support
+- `--port`: Port for SSE server (default: 3000)
+- `--base-url`: Base URL for SSE server (default: http://localhost:3000)
+- `--sse-path`: Path for SSE endpoint (default: /sse)
+- `--message-path`: Path for message endpoint (default: /message)
+
+Example:
+```bash
+mcphub run my-server --sse --port 3001
+```
+
+## Configuration File
+
+The CLI uses a `.mcphub.json` configuration file in your project directory. Here's an example structure:
+
+```json
+{
+  "mcpServers": {
+    "server-name": {
+      "package_name": "package-name",
+      "command": "command-to-run",
+      "args": ["arg1", "arg2"],
+      "env": {
+        "ENV_VAR": "value"
+      },
+      "description": "Server description",
+      "tags": ["tag1", "tag2"],
+      "last_run": "timestamp"
+    }
+  }
+}
+```
+
+## Features
+
+- Rich terminal interface with progress bars and colored output
+- Interactive prompts for configuration
+- Process management and monitoring
+- Server-Sent Events (SSE) support
+- Environment variable management
+- GitHub repository integration
+- Detailed status reporting
+- Process monitoring and management
+
+## Error Handling
+
+The CLI provides clear error messages and helpful suggestions when something goes wrong. Common error scenarios include:
+
+- Invalid GitHub repository URLs
+- Missing environment variables
+- Server configuration issues
+- Process management errors
+
+## Contributing
+
+To contribute to the CLI development:
+
+1. Fork the repository
+2. Create a feature branch
+3. Make your changes
+4. Add tests for new functionality
+5. Submit a pull request
+
+## License
+
+This project is licensed under the MIT License - see the LICENSE file for details.