Cabrit0 MCP Server Reunemacacada

A learning path generation server based on FastAPI that can create structured learning plans for any topic, integrate online resources, and optimize content organization and performance through intelligent algorithms.

Education and learning tools Knowledge management and memory #Learning Path #Resource Aggregation #Intelligent Algorithm #Performance Optimization .Python

rating : 2 points

downloads : 14

update time : 2025-04-29

What is the MCP Server?

The MCP Server is a powerful tool that can generate personalized learning paths based on topics you're interested in. It collects relevant resources from the Internet and organizes them into an easy - to - understand learning plan.

How to use the MCP Server?

Simply enter the topic you want to learn, and the server will create a customized learning path for you. You can choose the language, the number of resources, and the depth and breadth of the learning path.

Applicable Scenarios

Whether you're learning programming, history, or other fields, the MCP Server can provide you with an efficient learning solution.

Main Features

Cross - domain Learning Path GenerationSupports the generation of learning paths for various topics, not limited to the technical field.

Intelligent Resource FilteringUses the TF - IDF algorithm to filter the most relevant resources.

Multilingual SupportSupports Portuguese by default and can be switched to other languages.

Asynchronous Task SystemLong - running tasks can be processed asynchronously to improve the user experience.

YouTube Video IntegrationAdd relevant YouTube videos to the learning path.

Cache OptimizationGet results directly from the cache for repeated requests to speed up the response.

Advantages and Limitations

Advantages

Quickly generate personalized learning paths

Multilingual support

Efficient resource filtering mechanism

Optimized cache system

Limitations

Resources in some specific fields may be limited

Requires a stable network connection

How to Use

Access the MCP Server

Open a browser and navigate to the URL of the MCP Server.

Enter a Topic

Enter the topic you want to learn in the query parameters.

View Results

The server will return a JSON structure containing learning resources.

Usage Examples

Basic UsageGenerate a basic learning path about Python.

Customize the Number of NodesGenerate a learning path about machine learning with 20 nodes.

Asynchronous GenerationStart asynchronous generation of a learning path about artificial intelligence.

Frequently Asked Questions

How to clear the cache?

Does it support multiple languages?

How to check the status of an asynchronous task?

Related Resources

Official Documentation

Detailed API documentation and usage guide.

GitHub Repository

Open - source code repository.

Video Tutorial

Quick - start video.

🚀 MCP Server

MCP Server is a powerful tool designed for generating and managing knowledge graphs. It offers the following core capabilities:

Asynchronous task handling: All long-running operations are executed as asynchronous tasks.
Responsive generation: Dynamically generate knowledge graphs based on user requirements.
Intelligent caching system: Supports result caching to speed up responses for repeated queries.

✨ Features

Asynchronous Task System

Submit asynchronous tasks and obtain a taskId.
Support querying task status via taskId.
Provide a function to view the list of all tasks.

Knowledge Graph Generation

Filter the most relevant resources based on the TF-IDF method.
Support customizing knowledge graph structure parameters (width, depth, etc.).
Offer support for multiple languages and topics.

🔧 Technical Details

Caching Mechanism

Result caching: Accelerate response times for repeated queries.
Domain method caching: Remember the best scraping method for each domain name.
Resource filtering: Block irrelevant resources (such as images, style sheets, etc.) during the scraping process.

Technical Metrics

Response time optimization:
- For cached topics: Response time reduced by 60 - 80%.
- For new topics: Response time reduced by 30 - 50%.
Memory usage:
- Memory usage during scraping reduced by 40 - 60%.
Throughput improvement:
- Ability to handle concurrent requests increased by 3 - 5 times.

📦 Installation

Deploy with Docker

docker build -t mcp-server .
docker run -p 8080:8080 mcp-server

Platform Deployment

Supported platforms include:

Render
Fly.io
Other cloud platforms that support Docker containers or Python applications.

📚 Documentation

Basic Interfaces

Generate Knowledge Graph (Synchronous)

GET /generate_mcp?topic=python&language=en&category=technology

Asynchronous Generation

POST /generate_mcp_async?topic=machine+learning&num_nodes=20

Status Query

GET /status/550e8400-e29b-41d4-a716-446655440000

Cache Management

Clear Cache

POST /clear_cache?pattern=mcp:*&clear_domain_cache=true

Get Cache Statistics

GET /cache_stats

💻 Usage Examples

Performance Improvement

The MCP Server optimizes performance in the following ways:

Intelligent caching: Speed up response times for repeated queries.
Asynchronous processing: Improve system throughput.
Resource filtering: Reduce unnecessary bandwidth usage.
Domain adaptation: Remember the best scraping strategy.
Instance reuse pool: Reduce startup overhead.

Deployment Considerations

Environment Requirements

Operating system: Linux 64-bit or macOS.
Python version: 3.8+.
Memory requirement: Recommended 2GB+ RAM.
Disk space: At least 10GB of available space.

📄 License

The MCP Server is licensed under the following terms:

MCP Server - Knowledge Graph Generation Tool
© 2024 MCP Development Team. All rights reserved.

You may not use or distribute this software except in compliance with the license terms.