MCP Demo
A project demonstrating the MCP protocol, including a server, client, and debugging tool, supporting SSE communication and JWT authentication, and integrating LangChain/LangGraph technology.
2.5 points
8.5K

What is the MCP server?

The MCP server is a backend service that implements the Model Context Protocol, allowing clients to interact with AI models through SSE (Server-Sent Events). It supports basic streaming responses and can also be configured with JWT authentication to protect endpoints.

How to use the MCP server?

You can start the server by running the provided Python script, and then use the client to connect to the SSE endpoint for interaction. It also supports integration with LangChain/LangGraph as an AI model host.

Use cases

Suitable for application scenarios that require real-time AI model interaction, such as chatbots, streaming content generation, AI-assisted tools, etc. Particularly suitable for development projects that require SSE protocol support.

Main Features

SSE Protocol Support
Real-time data stream transmission based on Server-Sent Events
JWT Authentication
Optional security authentication method to protect your endpoints
LangChain Integration
Supports serving as an AI model host for LangChain/LangGraph
Debugging Tools
Provides a dedicated Inspector tool for debugging and testing
Advantages
Lightweight implementation, easy to deploy and integrate
Supports multiple usage methods (direct call/LangChain integration)
Provides visual debugging tools
Open-source project with community support
Limitations
Currently mainly supports the Python ecosystem
The SSE protocol may have compatibility issues in some network environments
Documentation and examples need to be improved

How to Use

Set up the environment
Create a Python virtual environment and install dependencies
Start the server
Choose to start a basic server or a server with JWT authentication
Run the client
Use the example client to connect to the server
LangChain Integration (Optional)
Use the server as an AI model host for LangChain/LangGraph

Usage Examples

Basic Chat Interaction
Implement basic chatbot functions using the SSE protocol
LangChain Integration
Use the MCP server as the AI model backend for LangChain applications
Debugging and Testing
Use the Inspector tool to debug the server response

Frequently Asked Questions

How to enable JWT authentication?
What if the Inspector tool cannot connect to the server?
Which AI models are supported?
How to extend custom functions?

Related Resources

Python SDK Code Repository
Official Python SDK implementation
HTTP Client Example
Example of MCP client implementation
Inspector Tool
Debugging and testing tool for the MCP protocol
Ollama Project
Run large language models locally

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

K
Klavis
Klavis AI is an open-source project that provides a simple and easy-to-use MCP (Model Context Protocol) service on Slack, Discord, and Web platforms. It includes various functions such as report generation, YouTube tools, and document conversion, supporting non-technical users and developers to use AI workflows.
TypeScript
8.8K
5 points
M
MCP
The Microsoft official MCP server provides search and access functions for the latest Microsoft technical documentation for AI assistants
9.3K
5 points
A
Aderyn
Aderyn is an open - source Solidity smart contract static analysis tool written in Rust, which helps developers and security researchers discover vulnerabilities in Solidity code. It supports Foundry and Hardhat projects, can generate reports in multiple formats, and provides a VSCode extension.
Rust
5.1K
5 points
D
Devtools Debugger MCP
The Node.js Debugger MCP server provides complete debugging capabilities based on the Chrome DevTools protocol, including breakpoint setting, stepping execution, variable inspection, and expression evaluation.
TypeScript
5.5K
4 points
S
Scrapling
Scrapling is an adaptive web scraping library that can automatically learn website changes and re - locate elements. It supports multiple scraping methods and AI integration, providing high - performance parsing and a developer - friendly experience.
Python
8.1K
5 points
M
Mcpjungle
MCPJungle is a self-hosted MCP gateway used to centrally manage and proxy multiple MCP servers, providing a unified tool access interface for AI agents.
Go
0
4.5 points
C
Cipher
Cipher is an open-source memory layer framework designed for programming AI agents. It integrates with various IDEs and AI coding assistants through the MCP protocol, providing core functions such as automatic memory generation, team memory sharing, and dual-system memory management.
TypeScript
0
5 points
N
Nexus
Nexus is an AI tool aggregation gateway that supports connecting multiple MCP servers and LLM providers, providing tool search, execution, and model routing functions through a unified endpoint, and supporting security authentication and rate limiting.
Rust
0
4 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
15.7K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
15.9K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
45.3K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
24.9K
5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
20.3K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
45.1K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
16.0K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
29.8K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIBase