> ## Documentation Index
> Fetch the complete documentation index at: https://docs.moorcheh.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP Overview

> Moorcheh MCP Server - Complete integration guide

# Moorcheh MCP Server

## What is MCP?

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.

## Moorcheh MCP Implementation

Our MCP server provides seamless integration with Moorcheh's comprehensive AI capabilities including document embedding, vector storage, semantic search, and AI-powered answer generation. This server enables you to interact with Moorcheh's services through the Model Context Protocol.

<CardGroup cols={2}>
  <Card title="Document Search" icon="magnifying-glass">
    Search through your uploaded documents using semantic similarity and natural language queries.
  </Card>

  <Card title="Document Retrieval" icon="download">
    Retrieve specific documents by their IDs for direct access to content and metadata.
  </Card>

  <Card title="Namespace Management" icon="folder">
    Create, list, and delete namespaces for organizing your data efficiently.
  </Card>

  <Card title="AI-Powered Answers" icon="sparkles">
    Get intelligent responses based on your stored data using advanced AI models.
  </Card>
</CardGroup>

## Quick Start Guide

There are two ways to use the Moorcheh MCP server:

<CardGroup cols={2}>
  <Card title="Option 1: NPX (Recommended)" icon="zap">
    No installation required - run directly with npx

    ```bash theme={null}
    MOORCHEH_API_KEY=your_api_key_here npx -y @moorchehai/mcp
    ```
  </Card>

  <Card title="Option 2: Manual Installation" icon="code">
    Clone and run locally for development

    * Clone the repository
    * Install dependencies
    * Configure environment
    * Start the server
  </Card>
</CardGroup>

## Key Features

<CardGroup cols={2}>
  <Card title="Standardization" icon="check-circle">
    Consistent interface across different data sources and tools, making integration easier.
  </Card>

  <Card title="Security" icon="shield-check">
    API key-based authentication ensures secure access to your data and resources.
  </Card>

  <Card title="Extensibility" icon="plus-circle">
    Easy to add new data sources and tools without changing your AI application.
  </Card>

  <Card title="Performance" icon="zap">
    Optimized for efficient data retrieval and processing in AI applications.
  </Card>
</CardGroup>

## Available Tools

### Namespace Management

<CardGroup cols={3}>
  <Card title="list-namespaces" icon="list">
    View all your available namespaces
  </Card>

  <Card title="create-namespace" icon="plus">
    Create a new namespace for storing data
  </Card>

  <Card title="delete-namespace" icon="trash">
    Remove a namespace and all its contents
  </Card>
</CardGroup>

### Data Operations

<CardGroup cols={5}>
  <Card title="upload-text" icon="upload">
    Upload text documents to a namespace
  </Card>

  <Card title="upload-file" icon="file-arrow-up">
    Directly upload files to a namespace
  </Card>

  <Card title="upload-vectors" icon="database">
    Upload vector embeddings to a namespace
  </Card>

  <Card title="get-data" icon="download">
    Retrieve documents by ID from text namespaces
  </Card>

  <Card title="delete-data" icon="trash">
    Remove specific data items from a namespace
  </Card>
</CardGroup>

### Search & AI

<CardGroup cols={2}>
  <Card title="search" icon="magnifying-glass">
    Search across namespaces with vector similarity
  </Card>

  <Card title="answer" icon="sparkles">
    Get AI-generated answers based on your search
  </Card>
</CardGroup>

## Supported AI Models

Our MCP server supports multiple advanced AI models for generating intelligent responses:

| Model                | Provider  | Description                                                                         |
| -------------------- | --------- | ----------------------------------------------------------------------------------- |
| Claude Sonnet 4.6    | Anthropic | Fast flagship: coding, tools, long docs and RAG (\~1M context).                     |
| Claude Opus 4.6      | Anthropic | Deepest reasoning and hardest tasks; pick when quality matters most (\~1M context). |
| Llama 4 Maverick 17B | Meta      | Long context, summarization, function calling, fine-tuning friendly.                |
| Amazon Nova Pro      | Amazon    | Chat, math, and structured answers for AWS-style workloads.                         |
| DeepSeek R1          | DeepSeek  | Step-by-step reasoning; math, logic, and technical explanations.                    |
| DeepSeek V3.2        | DeepSeek  | Efficient general Q\&A, multilingual, everyday RAG (\~164K context).                |
| OpenAI GPT OSS 120B  | OpenAI    | Large generalist: research-style answers and long-form writing.                     |
| Qwen 3 32B           | Qwen      | Code and bilingual (EN/ZH) tasks in a smaller footprint.                            |
| Qwen3 Next 80B A3B   | Qwen      | MoE model for long chats, docs, and code at scale (\~256K context).                 |

## Prerequisites

<CardGroup cols={3}>
  <Card title="Node.js" icon="node">
    Version 18.0.0 or higher
  </Card>

  <Card title="Moorcheh Account" icon="user">
    Active account with API access
  </Card>

  <Card title="Git" icon="github">
    For cloning the repository
  </Card>
</CardGroup>

## Next Steps

<CardGroup cols={3}>
  <Card title="Setup" icon="wrench" href="/integrations/mcp/setup">
    Learn how to install, configure, and start the MCP server
  </Card>

  <Card title="Configuration" icon="sliders" href="/integrations/mcp/configuration">
    Understand available tools, supported models, and troubleshooting
  </Card>

  <Card title="Introduction" icon="book" href="/integrations/mcp/introduction">
    Deep dive into MCP concepts and Moorcheh's implementation
  </Card>
</CardGroup>