What is Connectcloud Mcp Server

The connectcloud-mcp-server is a fully functional Model Context Protocol (MCP) server that allows users to connect to various data sources in CData Connect Cloud from Claude Desktop. It facilitates data querying and management through SQL and other operations.

Use cases

Use cases for connectcloud-mcp-server include data analysis using SQL queries, batch processing of data records, executing complex stored procedures, and managing metadata for cloud-based data applications.

How to use

To use connectcloud-mcp-server, you can install it via Smithery with the command: npx -y @smithery/cli install @CDataSoftware/connectcloud-mcp-server --client claude. Alternatively, you can manually clone the repository, install dependencies, and configure environment variables for authentication.

Key features

Key features include executing SQL queries on cloud-connected data sources, performing batch operations (INSERT, UPDATE, DELETE), executing stored procedures, accessing metadata (catalogs, schemas, tables, columns), and retrieving query execution logs.

Where to use

connectcloud-mcp-server is suitable for use in data management, analytics, and application development environments where integration with cloud data sources is required.

🧠 CData Connect Cloud MCP Server

A Model Context Protocol (MCP) server for querying and managing data through CData Connect Cloud. This server enables AI agents to interact with data using SQL, metadata introspection, and procedure execution.

✨ Features

• ✅ Execute SQL queries on cloud-connected data sources
• 🔄 Perform batch operations (INSERT, UPDATE, DELETE)
• ⚙️ Execute stored procedures
• 📚 Access metadata (catalogs, schemas, tables, columns)

🛠 Prerequisites

• Node.js v18 or higher
• A CData Connect Cloud account with API access
• A Personal Access Token (PAT) for authentication

⚙️ Setup

Installing via Smithery

To install CData Connect Cloud MCP Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @CDataSoftware/connectcloud-mcp-server --client claude

Manual Installation

1. Clone the repository

   git clone https://github.com/cdatasoftware/connectcloud-mcp-server.git
   cd connect-cloud-mcp-server
   

2. Install dependencies

   npm install
   

3. Configure environment variables

   Create a .env file with the following content:

   CDATA_USERNAME=your_username
   CDATA_PAT=your_personal_access_token
   
   # Optional
   LOG_ENABLED=false
   LOG_LEVEL=info
   CDATA_URL=https://your-test-environment-url
   

▶️ Running the Server

Development Mode

Use ts-node for live development:

npm run dev

Production Mode

Build and start:

npm run build
npm start

🧰 Available Tools

🔹 Data Operations

🔹 Metadata Operations

🤖 Usage with LLMs

This server is compatible with AI agents that implement the Model Context Protocol.

Example (TypeScript + MCP Agent)

const response = await agent.generateContent({
  tools: [
    {
      name: "queryData",
      parameters: {
        query: "SELECT * FROM Salesforce1.Salesforce.Account LIMIT 10"
      }
    }
  ]
});

🐳 Running in Docker

Build the image

docker build -t mcp/connectcloud:latest -f Dockerfile .

🧩 Claude Desktop Integration

Add or edit this configuration to your claude_desktop_config.json under the mcpServers section:

🔹 From Docker

{
  "mcpServers": {
    "connect-cloud": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "--name",
        "connect-cloud-mcp",
        "-e",
        "CDATA_USERNAME",
        "-e",
        "CDATA_PAT",
        "mcp/connectcloud"
      ],
      "env": {
        "CDATA_USERNAME": "<your-cdata-username>",
        "CDATA_PAT": "<your-cdata-personal-access-token>"
      }
    }
  }
}

Via Npx

{
  "mcpServers": {
    "connect-cloud": {
      "command": "npx",
      "args": [
        "-y",
        "@cdatasoftware/connectcloud-mcp-server"
      ],
      "env": {
        "CDATA_USERNAME": "<your-cdata-username>",
        "CDATA_PAT": "<your-cdata-personal-access-token>"
      }
    }
  }
}

📄 License

This project is licensed under the MIT License.