MCP ExplorerExplorer

Mcp Contentstack

@viveksingh-ctrlon a year ago
3 MIT
FreeCommunity
AI Systems

Overview

What is Mcp Contentstack

Claude 3.7 Sonnet MCP Interface is a project that facilitates interactions with the Claude 3.7 Sonnet language model using the Model Context Protocol (MCP), enabling both graphical and command-line interfaces for efficient tool interactions and development.

Use cases

The interface can be used for a variety of applications including tool development, testing interactions with the Claude model, and integrating custom functionalities into workflows. Users can leverage both GUI and CLI interfaces to engage with Claude effectively.

How to use

To use the Claude Desktop, start the application, connect it to a compatible MCP tool server, and begin interacting with Claude through the GUI. For CLI access, set up the environment, configure the .env file with your AWS credentials, and run the client script to start engaging with Claude via command line.

Key features

Key features include a GUI for visual interaction with Claude, CLI support for automatic tool discovery and execution, seamless integration with AWS Bedrock, markdown support, and a lightweight architecture that allows for easy tool development and testing.

Where to use

Claude 3.7 Sonnet MCP Interface can be used in various environments, including local setups for development and testing of tools, as well as in production scenarios where enhanced interactions with LLMs are required through either a desktop application or a command-line interface.

Content

Claude 3.7 Sonnet MCP Interface

This project enables powerful, LLM-agnostic interactions with Claude 3.7 Sonnet, either via the Claude Desktop (MCP GUI) or directly through a command-line client using AWS Bedrock and the MCP protocol.


🧭 Options for Usage

You can interact with Claude in two ways:


🖥️ 1. Using Claude Desktop (GUI with MCP Server)

Claude Desktop provides a graphical interface for working with Claude via the MCP protocol. It is ideal for users who want a visual tool experience.

✅ Features

  • GUI-based interaction with Claude
  • Tool registration and calls via local or remote servers
  • Plug-and-play tool development and testing

🚀 Usage

  1. Start Claude Desktop

    • Run the application
    • Point it to your local or remote MCP-compatible tool server ( fastmcp install server_name.py )
  2. Connect a tool server

    • Claude Desktop uses MCP’s stdio or http transport to connect to tool providers.
  3. Start chatting

    • You can test tool calling, observe Claude’s responses, and debug tool output.

📦 For more info, visit: https://github.com/ai-sdk/mcp


🧑‍💻 2. Using MCP Client Directly (CLI via Bedrock)

This CLI tool connects to Claude through AWS Bedrock and automatically handles tool calling using the MCP protocol.

✨ Features

  • CLI-driven interaction with Claude 3.7 Sonnet
  • Automatic tool discovery via MCP
  • Tool call execution and response routing
  • Rich UI with markdown, syntax highlighting, and spinners
  • Lightweight and extensible

📦 Setup

curl -LsSf https://astral.sh/uv/install.sh | sh
git clone https://github.com/your-username/claude-mcp-client.git
cd claude-mcp-client
uv venv .venv
source .venv/bin/activate  # or .venv\Scripts\activate on Windows
uv pip install -r requirements.txt

Create a .env file in the root:

AWS_ACCESS_KEY_ID=your-access-key
AWS_SECRET_ACCESS_KEY=your-secret-key
AWS_REGION=us-east-1
AUTHTOKEN=bltsomething
BRAND_KIT_UID=cssomething

🧠 Model used: us.anthropic.claude-3-7-sonnet-20250219-v1:0

🚀 Running the Client

python client.py ./brand-kit/knowledge-vault/crud.py

Example Tool Server

# tool_server.py
from mcp.server.fastmcp import FastMCP 
server = FastMCP()
@server.tool()
class AddTool(Tool):
    name = "add"
    description = "Adds two numbers"
    input_schema = {"a": "number", "b": "number"}

    async def call(self, input):
        return input["a"] + input["b"]

if __name__ == "__main__":
    server.run()

🧠 Interaction Flow

  • The CLI maintains a conversation history (configurable)
  • Claude can detect when a tool is needed and call it automatically
  • Tool responses are routed back to Claude for follow-up
  • Everything is streamed and displayed beautifully in your terminal

💡 Type quit anytime to exit.


🛠 Architecture Overview

Claude (via AWS Bedrock)
        |
      Client.py
        |
    ┌────────────┐
    │ MCP Server │  <── Tool: Python or JS
    └────────────┘

🧹 Cleanup

The client ensures graceful shutdown using AsyncExitStack and aclose() to clean up all sessions.


🖼️ Interface Preview

Here’s a quick look at Claude Desktop in action:

Screenshot 2025-05-01 at 11 09 25 PM

🛡 License

MIT License


🙏 Credits

Tools

No tools

Comments

Recommend MCP Servers

View All MCP Servers