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.
rating : 2.5 points
downloads : 16
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 SupportReal-time data stream transmission based on Server-Sent Events
JWT AuthenticationOptional security authentication method to protect your endpoints
LangChain IntegrationSupports serving as an AI model host for LangChain/LangGraph
Debugging ToolsProvides a dedicated Inspector tool for debugging and testing
Advantages and Limitations
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 InteractionImplement basic chatbot functions using the SSE protocol
LangChain IntegrationUse the MCP server as the AI model backend for LangChain applications
Debugging and TestingUse 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
Featured MCP Services

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
1.7K
5 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
823
4.3 points

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
79
4.3 points

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
130
4.5 points

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#
554
5 points

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
6.6K
4.5 points

Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
5.2K
4.7 points

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
745
4.8 points