Custom MCP Server for Cursor

MCP - Question-Answer System with RAG

MCP is an advanced question-answering system using the Retrieval-Augmented Generation (RAG) technique to provide accurate and contextual answers based on a corpus of documents.

Features

🔍 Semantic search in documents
💾 Smart caching with Redis
📊 Persistent storage with MongoDB
🤖 Integration with OpenAI for embeddings and text generation
📈 System monitoring and metrics
🔄 Asynchronous operations management

Prerequisites

Python 3.9+
MongoDB Community Edition
Redis
OpenAI API Key

Facility

Clone the repository:

git clone https://github.com/votre-username/mcp.git
cd mcp

Install system dependencies:

# MongoDB
brew tap mongodb/brew
brew install mongodb-community
brew services start mongodb-community

# Redis
brew install redis
brew services start redis

Configure the Python environment:

python -m venv .venv
source .venv/bin/activate  # Sur Unix/macOS
pip install -r requirements.txt

Configure environment variables:

cp .env.example .env
# Éditer .env avec vos configurations

Quick use

from src.rag import RAGWorkflow

# Initialisation
rag = RAGWorkflow()

# Ingestion de documents
await rag.ingest_documents("chemin/vers/documents")

# Interrogation
response = await rag.query("Votre question ici ?")

Documentation

Tests

python -m pytest tests/ -v

Project structure

mcp/
├── src/
│   ├── __init__.py
│   ├── rag.py              # Workflow RAG principal
│   ├── models.py           # Modèles de données
│   ├── mongo_operations.py # Opérations MongoDB
│   ├── redis_operations.py # Opérations Redis
│   └── database.py         # Configuration de la base de données
├── tests/
│   ├── __init__.py
│   ├── test_mcp.py
│   └── test_mongo_integration.py
├── prompts/
│   ├── system_prompt.txt
│   ├── query_prompt.txt
│   └── response_prompt.txt
├── docs/
│   ├── installation.md
│   ├── usage.md
│   ├── architecture.md
│   └── api.md
├── requirements.txt
├── .env.example
└── README.md

Contribution

Fork the project
Create a branch for your feature ( git checkout -b feature/AmazingFeature )
Commit your changes ( git commit -m 'Add some AmazingFeature' )
Push to branch ( git push origin feature/AmazingFeature )
Open a Pull Request

License

This project is licensed under the MIT License. See the LICENSE file for details.

Contact

Your Name - @your_twitter

Project link: https://github.com/your-username/mcp

This server cannot be installed

security - not tested

license - not found

quality - not tested

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

Connects to Cursor and enables deep web searches via Linkup and RAG capabilities using LlamaIndex.

Related MCP Servers

MCP Tavily Search Server
spences10
A
security
A
license
A
quality
Integrates Tavily's search API with LLMs to provide advanced web search capabilities, including intelligent result summaries, domain filtering for quality control, and configurable search parameters.
Last updated -
3
64
9
JavaScript
MIT License
Search MCP Server
fengin
-
security
A
license
-
quality
The Search MCP Server enables seamless integration of network and local search capabilities in tools like Claude Desktop and Cursor, utilizing the Brave Search API for high-concurrency and asynchronous requests.
Last updated -
1
52
Python
MIT License
Tavily MCP Server with Proxy Support
tulong66
-
security
F
license
-
quality
Enables LLMs to perform sophisticated web searches through proxy servers using Tavily's API, supporting comprehensive web searches, direct question answering, and recent news article retrieval with AI-extracted content.
Last updated -
1
Python
Tavily MCP Server
RamXX
-
security
A
license
-
quality
Provides AI-powered web search capabilities using Tavily's search API, enabling LLMs to perform sophisticated web searches, get direct answers to questions, and search recent news articles.
Last updated -
53
Python
MIT License

View all related MCP servers

Appeared in Searches

Information about Superman