CData Connect Cloud

Provides access to CData Connect Cloud data sources via an MCP server with local-node execution.

javascript

GitHub Stars

javascript

Language

7 months ago

First Indexed

3 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": {
    "r3-yamauchi-cdata-connect-cloud-mcp-server": {
      "command": "node",
      "args": [
        "[cdata-connect-cloud-mcp-serverを配置したパス]/server.js"
      ],
      "env": {
        "CDATA_CONNECT_CLOUD_PAT": "CData Connect Cloud へ接続するための PAT",
        "CDATA_CONNECT_CLOUD_USER": "CData Connect Cloud へ接続するユーザー名",
        "CDATA_CONNECT_CLOUD_CATALOG_NAME": "CData Connect Cloud の Connection Name"
      }
    }
  }
}

This MCP server provides a bridge to CData Connect Cloud, enabling you to access CData Connect Cloud data sources from MCP clients. It runs as a local process and is configured via a client application, letting you connect, authenticate, and query through a simple, centralized server.

How to use

You interact with the CData Connect Cloud MCP Server through your MCP client. Start the local server as described, then point your client at the configured MCP entry to access CData Connect Cloud data sources. The server runs locally, and environment variables supply your authentication and target connection details. You do not need to modify protocol-level settings yourself; just ensure the server is running and your client is configured to use it.

Key usage patterns include: setting up your client to connect to the local MCP endpoint, supplying your Connect Cloud credentials, and selecting the specific catalog or connection you want to query. If you need to switch to a different Connect Cloud catalog or user, update the environment variables in the server configuration and restart the server to apply changes.

How to install

Prerequisites you need before running the MCP server: install Node.js 18 or later on your machine.

Step 1. Download the source code and place it in a path that contains only ASCII characters and no spaces. Choose any suitable path on your system.

Step 2. Install Node.js 18 or later. Ensure the node and npm commands are available in your shell or terminal.

Step 3. Install dependencies for the MCP server package.

npm i

Step 4. Configure the Claude Desktop application by adding the MCP server entry to claude_desktop_config.json. Use the provided JSON structure to wire in the server.

{
  "mcpServers": {
    "cdata_connect_cloud": {
      "command": "node",
      "env": {
        "CDATA_CONNECT_CLOUD_CATALOG_NAME": "CData Connect Cloud の Connection Name",
        "CDATA_CONNECT_CLOUD_USER": "CData Connect Cloud へ接続するユーザー名",
        "CDATA_CONNECT_CLOUD_PAT": "CData Connect Cloud へ接続するための PAT"
      },
      "args": [
        "[cdata-connect-cloud-mcp-serverを配置したパス]/server.js"
      ]
    }
  }
}

Step 5. Restart the Claude Desktop application after saving the claude_desktop_config.json changes. If the application appears to be running in the background, right-click the tray icon and choose Quit to fully terminate it before relaunching.

Additional notes and configuration

The MCP server is configured to use a local Node.js process. The environment variables provide the necessary credentials and catalog information for CData Connect Cloud. If you need to change your connection details, update the environment variables in the configuration and restart the MCP server.

Environment variables shown in the example include:

CDATA_CONNECT_CLOUD_CATALOG_NAME: the name of the CData Connect Cloud catalog to connect to
CDATA_CONNECT_CLOUD_USER: the username to authenticate with Connect Cloud
CDATA_CONNECT_CLOUD_PAT: a personal access token for Connect Cloud authentication

Built by

VeilStrat

AI signals for GTM teams