Moorcheh

Provides namespaces, document and vector operations, semantic search, and AI-powered answers via the Moorcheh MCP Server.

typescript

2

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "moorcheh-ai-moorcheh-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@moorchehai/mcp"
      ],
      "env": {
        "MOORCHEH_API_KEY": "your_actual_api_key_here"
      }
    }
  }
}

The Moorcheh MCP Server lets you interact with Moorcheh’s Embedding, Vector Store, Search, and Gen AI Answer services through a unified Model Context Protocol interface. It enables you to manage namespaces, upload and retrieve documents and embeddings, perform semantic searches, and generate AI-powered answers from your data.

How to use

You connect to the Moorcheh MCP Server from your MCP client to perform core data operations and AI-enabled queries. Use the server to manage namespaces, upload documents and vectors, run semantic searches, and request AI-generated answers based on your stored data. Start by providing your API key to authorize requests, then issue actions against available namespaces to organize and retrieve your content.

A typical workflow looks like this: create a namespace for a project, upload your text documents or embeddings, search within that namespace for relevant results, and request an AI answer that combines search results with your data context. You can sequence these steps to build a data-backed Q&A experience or a focused document retrieval system.

How to install

Prerequisites you need before install: Node.js version 18.0.0 or higher, a Moorcheh account with API access, and Git for cloning repositories.

Option 1: NPX (Recommended — No Installation Required) Set your API key and run directly.

MOORCHEH_API_KEY=your_api_key_here npx -y @moorchehai/mcp

Option 2: Manual Installation If you prefer to clone and run locally.

# Step 1: Clone the repository
git clone https://github.com/moorcheh-ai/moorcheh-mcp.git
cd moorcheh-mcp

# Step 2: Install dependencies
npm install

Additional setup and start

Set up your API key in a local environment file so the server can authenticate requests.

# Copy the example environment file then edit
cp env.example .env
# Open .env and replace with your actual API key
MOORCHEH_API_KEY=your_actual_api_key_here

Start the MCP server after configuration.

npm start

Security and keys

Keep your API key secret. Store it in a secure environment file and do not commit it to source control. Revoke and replace keys if you suspect exposure.

Notes

If you plan to integrate with Claude Desktop or Cursor IDE, you can configure MCP connections to run via NPX or local installation as shown in their respective setup guides. Ensure you provide the correct API key in each configuration.

Available tools

list-namespaces

List all available namespaces to see where you can store data.

create-namespace

Create a new namespace for organizing your documents and embeddings.

delete-namespace

Remove a namespace and all its contents.

upload-text

Upload text documents to a specific namespace.

upload-vectors

Upload vector embeddings to a namespace.

get-data

Retrieve documents by ID from a text namespace.

delete-data

Delete specific data items from a namespace.

search

Perform semantic search across namespaces using vector similarity.

answer

Generate AI-powered answers based on the top results from searches.