MCP Server Reunemacacada

A learning path generation server based on FastAPI that can automatically aggregate online resources according to topics and organize them into structured learning routes, supporting multiple languages and intelligent resource screening.

Education and learning tools Knowledge management and memory #Learning Path #Resource Aggregation #Intelligent Generation #Multi - language .Python

rating : 2 points

downloads : 7.7K

update time : 2025-04-29

Open Site

What is MCP Server?

MCP Server is an intelligent learning path generation system that can automatically create structured learning plans for any topic. It aggregates relevant resources from the web and organizes them into learning paths in a logical order to help users systematically master new knowledge.

How to use MCP Server?

It's very easy to use. Simply provide a topic name, and the server will automatically generate a learning path containing relevant resources. You can call it directly through the API, and it also provides asynchronous processing options and a caching mechanism to optimize the experience.

Use cases

It is suitable for scenarios such as individual self - study, curriculum design in educational institutions, and enterprise training planning. Whether it's technical learning or humanities and social sciences, it can generate suitable learning paths. It's especially suitable for users who need to systematically learn new fields.

Main Features

Multi - topic support

Not limited to technical topics, it supports learning path generation in any field.

Intelligent resource aggregation

Automatically searches and crawls relevant learning resources from the web.

Multi - language support

It is specially optimized for Portuguese and also supports multiple languages.

TF - IDF resource filtering

Uses intelligent algorithms to ensure that resources are highly relevant to the topic.

YouTube video integration

Automatically includes relevant YouTube video resources.

Asynchronous task system

Supports asynchronous processing of long - running tasks and provides progress feedback.

Intelligent caching system

Optimizes response speed and reduces redundant calculations.

Advantages

Automatically generates structured learning paths, saving planning time.

Integrates various types of learning resources (articles, videos, etc.).

Supports customizing the depth and breadth of learning paths.

The intelligent caching system improves response speed.

Optimized web crawling technology ensures resource quality.

Limitations

Depends on the availability and quality of online resources.

Complex topics may require manual adjustment of learning paths.

The free version may have limitations on the number of resources.

Support for some languages may not be as comprehensive as that for mainstream languages.

How to Use

Prepare the environment

Ensure that you have available API access rights and an internet connection.

Select a topic

Determine the topic you want to learn or generate a learning path for.

Call the API

Use a simple HTTP request to call the generation interface.

Get the result

Receive a structured learning path in JSON response.

Customize parameters (optional)

Adjust parameters such as the number of nodes and language as needed.

Usage Examples

Learning a programming language

Generate a learning path for the Python programming language.

History learning

Generate learning resources for the history of Brazil.

Getting started with machine learning

Create a learning plan for machine learning.

Asynchronous generation of large - scale learning paths

Generate a complex learning path containing a large number of resources.

Frequently Asked Questions

Which languages does MCP Server support?

How long does it usually take to generate a learning path?

How to ensure the reliability of resources?

Can I customize the structure of learning paths?

Are there any usage limits?

How to clear the cache?

Related Resources

API Reference Documentation

Complete description of API parameters and response formats.

Flutter Integration Guide

How to use MCP Server in a Flutter application.

Performance Optimization Instructions

Technical details of server performance optimization.

GitHub Repository

Project source code (private).

Online Demo

Production - environment demonstration server.

🚀 MCP Server

The MCP Server is a powerful tool designed to generate MCPs efficiently. It offers various interfaces for both synchronous and asynchronous operations, and it has been optimized for performance.

🚀 Quick Start

📦 Installation

First, you need to install the necessary dependencies. Run the following command:

pip install mcp_server

▶️ Starting the Server

After installation, start the server using the following command:

python3 -m mcp_server.runserver --port 8080

💻 Usage Examples

🔍 Basic Usage

from mcp_server.client import MCPClient

client = MCPClient('http://localhost:8080')

# Generate MCP asynchronously
task_id = client.generate_mcp_async(topic='inteligência+artificial', category='technology')

# Check task status
status = client.check_status(task_id)
print(status)  # Print task status

📚 Documentation

🔌 API Interfaces

1️⃣ Synchronous Interfaces

Generate MCP (Synchronous):

GET /generate_mcp?topic=主题

Custom Parameters:

GET /generate_mcp?topic=machine+learning&num_nodes=20

English Language:

GET /generate_mcp?topic=javascript&language=en

2️⃣ Asynchronous Interfaces

Submit Task:

POST /generate_mcp_async?topic=inteligência+artificial&category=technology

Check Status:

GET /status/{task_id}

🔧 Technical Details

🚀 Key Technologies

Caching Mechanism: Store results in memory to reduce the time consumption of repeated queries.
Asynchronous Task Processing: Long - running operations are executed by background threads, without affecting the main program's response speed.
Resource Filtering: Use the TF - IDF algorithm to automatically select the most relevant content.
Optimized Crawling Technology: Improve web page crawling efficiency and reduce resource consumption.

📊 Performance Data

Cache Hit: Reduce query time by 60 - 80%.
New Topic Processing: Save 30 - 50% of the time.
Memory Usage: Achieve a 40 - 60% optimization effect.
Throughput Improvement: Increase concurrent capacity by 3 - 5 times.

🚢 Deployment

🐳 Docker Deployment

docker build -t mcp_server .
docker run -p 8080:8080 mcp_server

🌐 Platform Deployment

Deploy according to the documentation provided by specific platforms (such as Render, Fly.io). It is generally recommended to use Docker containers.

📄 License

Copying, distributing, modifying, publicly displaying, or performing this software without permission is strictly prohibited. This software is only available to paid - subscription users.