Skip to main content

​
MCP Introduction

​
What is Model Context Protocol?

The Model Context Protocol (MCP) is an open standard that enables AI models to interact with external data sources, tools, and services in a secure and standardized way. It provides a common interface for AI applications to access various resources without needing to understand the specific implementation details of each service. Think of MCP as a universal translator that allows AI models to communicate with different data sources and tools using a common language, regardless of how those services are implemented.

​
Why Use MCP?

Standardization

Consistent interface across different data sources and tools, making integration easier.

Security

Built-in security features ensure safe access to your data and resources.

Extensibility

Easy to add new data sources and tools without changing your AI application.

Performance

Optimized for efficient data retrieval and processing in AI applications.

​
MCP Architecture

Client

Your AI application that needs to access external data or tools. The client makes requests to servers through the MCP protocol.

Server

The MCP server (like Moorcheh) that provides access to specific data sources or tools. It handles authentication, data retrieval, and response formatting.

Protocol

The standardized communication protocol that defines how clients and servers interact, including message formats, authentication, and error handling.

​
Moorcheh MCP Implementation

Our MCP server provides access to Moorcheh’s comprehensive AI capabilities including document embedding, vector storage, semantic search, and AI-powered answer generation through a standardized interface. This allows AI applications to:
  • Search through uploaded documents using natural language queries
  • Retrieve specific documents by their IDs
  • Upload new documents to namespaces
  • Manage namespaces and document organization
  • Access document metadata and content
  • Generate AI-powered answers based on stored data

​
Basic MCP Request Example

Example MCP Request
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "search_documents",
    "arguments": {
      "query": "machine learning algorithms",
      "namespace": "tech_docs",
      "limit": 5
    }
  }
}

​
Getting Started

To start using Moorcheh’s MCP implementation:
  1. Set up your Moorcheh account and get your API key
  2. Choose between NPX (recommended) or manual installation
  3. Configure your MCP client to connect to our MCP server
  4. Test the connection with a simple search request
  5. Integrate the MCP functions into your AI application
  6. Explore advanced features like document upload and namespace management

​
Next Steps

Continue to the Setup section to learn how to configure your MCP client and establish a connection to Moorcheh’s MCP server.