MCP Arcknowledge

🚀 MCP Heterogeneous Knowledge Base Query System

The MCP (Multiple Content Processing) Heterogeneous Knowledge Base Query System is a multi-source data processing tool based on RAG (Retrieval-Augmented Generation) technology. It helps users extract and integrate information from multiple different document sources to solve complex problems.

🚀 Quick Start

The MCP system is a powerful tool for multi - source data processing. It allows users to manage knowledge sources and perform various queries efficiently.

✨ Features

Knowledge Source Management

• Add new knowledge document sources.
• List all registered knowledge sources.

Content Query

• Query a single knowledge base.
• Query a specified combination of knowledge bases.
• Query all knowledge bases.

📦 Installation

Project Structure

mcp-arcknowledge/
├── main.py          # Main program file
├── README.md        # Documentation
└── requirements.txt # Dependency management

Development Environment Configuration

1. Create the mcp.json configuration file:

{
    "name": "mcp-webhook-ai-agent",
    "version": "1.0.0",
    "description": "AI agent supporting Webhook with RAG functionality",
    "main": "main.py",
    "tools": [
        {
            "name": "set_document_source",
            "description": "Register a new document source URL for RAG operations"
        },
        {
            "name": "list_document_sources",
            "description": "List all registered document sources"
        },
        {
            "name": "query_rag",
            "description": "Use RAG to query a specified document source"
        },
        {
            "name": "process_post_query",
            "description": "Process a POST request containing a query payload"
        }
    ],
    "dependencies": {
        "fastmcp": ">=0.4.0",
        "requests": ">=2.31.0",
        "pydantic": ">=2.0.0"
    }
}

2. Configure Cursor AI:

   • Open the Cursor AI settings.
   • Navigate to the MCP section.
   • Add the path to the mcp.json file.
   • Restart Cursor AI to apply the changes.

3. Verify the configuration:

# Check if MCP is correctly configured
fastmcp check mcp.json

# List available tools
fastmcp list

💻 Usage Examples

Core Functions

1. add_new_knowledge_document_source(url: str, description:str = None, apikey:str = None) -> str

   • Function: Register a new document source URL, optionally providing a description and an API key.
   • Return: A confirmation message containing the new source ID.

2. list_knowledge_document_sources() -> Dict[str, Dict[str, str]]

   • Function: List all registered document sources.
   • Return: A dictionary with source IDs as keys and detailed information (URL, description, API key) as values.

3. query_knowledge_base(query: str, source_ids: List[str] = [], image: str = '') -> str

   • Function: Query text content using specified document sources (or all sources).
   • Return: A JSON string containing the results.

🚀 Project Development

Runtime Environment

• Recommended language version:
  • Python 3.8+

Start in Development Mode

# Start the development server
fastmcp run main.py

🤝 Contribution Guidelines

1. Format your code before submitting it.
2. Include unit tests when submitting a PR.

📄 License

This project is licensed under the MIT License.