How to Access Live RabbitMQ Data in Visual Studio Code via Cline

Cline is an autonomous coding agent right in your IDE, capable of creating/editing files, running commands, using the browser, and more with your permission every step of the way. When paired with CData API Driver for MCP Server, you get live access to CRM data within your IDE, enabling you to build, test, and validate data-driven features using real-time schema and records without ever leaving your development environment.

CData MCP Server provides schema-aware context to AI tools — whether you're using it for AI-assisted code generation in IDEs like Cursor and Cline, or for querying live data through chat interfaces like Claude Desktop.

This article outlines how to run CData API Driver for MCP Server on WSL (Windows Subsystem for Linux) and connect to it from the Cline extension in Visual Studio Code on Windows.

Background

MCP Server is typically designed for clients like Claude Desktop. However, when attempting to use it via the Cline extension in Windows VS Code, the following error occurred:

MCP error -32000: Connection closed

This issue is suspected to be caused by I/O handling problems in the stdio transport implementation on the Windows version of the Cline extension.

• Related GitHub Issue: https://github.com/cline/cline/issues/3464
• Additionally, environment variables such as PATH may not be inherited correctly when launching processes like Java or Node.

Prerequisites

• Visual Studio Code installed on Windows
• Cline extension installed and configured in VS Code
• Windows Subsystem for Linux (WSL) installed with a working Linux distribution (e.g., Ubuntu)
• Java 21+ JRE installed in WSL
• CData API Driver for MCP Server installed on Windows

Step 1: Authenticate with RabbitMQ (on Windows)

Before running MCP Server in WSL, you must complete authentication flow in a Windows environment. This ensures all necessary credentials are generated and stored properly. Find and run "CData API Driver for MCP Server" or execute the JAR file to open the configuration wizard.

java -jar "C:\Program Files\CData\CData MCP Server for RabbitMQ 20XX\lib\cdata.mcp.api.jar"

Connecting to RabbitMQ

About RabbitMQ Management HTTP API

RabbitMQ is an open-source message broker that supports multiple messaging protocols. The RabbitMQ Management HTTP API provides HTTP-based access to management and monitoring data for a RabbitMQ server. The API exposes information about virtual hosts, exchanges, queues, bindings, connections, channels, consumers, users, permissions, policies, and cluster-wide statistics.

The Management plugin must be enabled on the RabbitMQ server for the HTTP API to be available. By default, the management interface listens on port 15672.

Using Basic Authentication

RabbitMQ Management HTTP API uses HTTP Basic authentication. You must supply the username and password of a RabbitMQ management user.

To enable access to the management API:

1. Ensure the RabbitMQ Management plugin is enabled on your server (rabbitmq-plugins enable rabbitmq_management).
2. Use an existing management user or create one with the appropriate management tag (management, policymaker, monitoring, or administrator).
3. Note the full base URL of your RabbitMQ Management HTTP API (e.g., http://localhost:15672).

After configuring your RabbitMQ server, set the following connection properties to connect:

• AuthScheme: Set this to Basic.
• URL: Set this to the base URL of your RabbitMQ Management HTTP API (e.g., http://localhost:15672).
• User: Set this to your RabbitMQ management username (e.g., guest).
• Password: Set this to your RabbitMQ management password.

Example connection string:

Profile=C:\profiles\RabbitMQ.apip;AuthScheme=Basic;URL=http://localhost:15672;User=guest;Password=guest;

Available Tables

The RabbitMQ profile provides access to the following tables:

• Overview - Cluster-wide statistics and information about the RabbitMQ node
• Nodes - Information about individual nodes in the RabbitMQ cluster
• NodeMemory - Detailed memory usage breakdown for a specific cluster node
• Connections - List of all open AMQP connections to the broker
• Channels - List of all open AMQP channels across all connections
• Consumers - List of all consumers registered across all queues
• Exchanges - List of exchanges declared across all virtual hosts
• Queues - List of queues declared across all virtual hosts
• Bindings - List of all bindings between exchanges and queues
• VirtualHosts - List of virtual hosts configured on the broker
• VhostPermissions - User permissions within a specific virtual host
• Users - List of all RabbitMQ users
• Permissions - Permission records for all users across all virtual hosts
• TopicPermissions - Topic-level permission records for all users
• Policies - List of policies applied to queues and exchanges in virtual hosts
• OperatorPolicies - List of operator policies applied to queues in virtual hosts
• Parameters - List of component parameters (e.g., federation, shovel) per virtual host
• GlobalParameters - List of global parameters that apply across all virtual hosts
• VhostLimits - Resource limits configured for specific virtual hosts
• UserLimits - Resource limits configured for specific users
• FeatureFlags - List of feature flags and their enabled/disabled state on the node
• DeprecatedFeatures - List of deprecated features and their usage state
• AuthAttempts - Authentication attempt statistics for the node
• ClusterName - The name of the RabbitMQ cluster
• WhoAmI - Information about the currently authenticated management user
• ExchangeBindingsSource - Bindings for which a specific exchange is the source
• ExchangeBindingsDestination - Bindings for which a specific exchange is the destination
• QueueBindings - Bindings for a specific queue within a virtual host

Configuring MCP Server

Name your configuration (e.g. cdataapi), enter the required connection properties, and click "Connect."

Upon successful connection, the following directory and files will be created:

C:\Users\<username>\AppData\Roaming\CData\api Provider\
 |-- cdataapi.mcp
 |-- (other supporting config files)

Step 2: Copy the MCP Server Configuration into WSL

Next, copy the entire configuration folder from Windows into your WSL environment.

mkdir -p ~/.config/CData/
cp -r /mnt/c/Users/<username>/AppData/Roaming/CData/"api Provider" ~/.config/CData/

Ensure the destination path matches exactly: ~/.config/CData/api Provider/.

Step 3: Install MCP Server on WSL

Install Java and place the MCP Server JAR in the desired location within WSL:

sudo apt update
sudo apt install openjdk-21-jre-headless
sudo mkdir -p /opt/cdata/mcp_api/lib
sudo cp /mnt/c/Program\ Files/CData/CData\ Code\ Assist\ MCP\ for\ RabbitMQ\ 20XX/lib/cdata.mcp.api.jar /opt/cdata/mcp_api/lib/

Step 4: Configure Cline

Now, configure the Cline extension to launch MCP Server inside WSL using the wsl command.

Create or update cline_mcp_settings.json with the following content:

{
  "mcpServers": {
    "cdataapi": {
      "autoApprove": ["*"],
      "disabled": false,
      "timeout": 60,
      "type": "stdio",
      "command": "wsl",
      "args": [
        "-d",
        "Ubuntu", // Replace with your installed WSL distro name
        "--",
        "/usr/bin/java",
        "-jar",
        "/opt/cdata/mcp_api/lib/cdata.mcp.api.jar",
        "cdataapi"
      ],
      "env": {
        "JAVA_TOOL_OPTIONS": "-Xmx2g"
      }
    }
  }
}

Note: Replace Ubuntu with your actual WSL distribution name (e.g., Ubuntu-22.04). Run wsl -l in PowerShell or CMD to confirm.

Step 5: Interact with Live Data in Cline

From within Visual Studio Code, you can now run MCP commands through the Cline extension.

cdataapi_get_tables
cdataapi_get_columns AuthAttempts

If configured correctly, these commands will return a list of available RabbitMQ objects and metadata, allowing you to interact with your CRM schema in real time.

Try natural language prompts like:

• "Generate a React form to create a new RabbitMQ Lead."
• "Write a Python function to pull Opportunities closed this quarter."

Build with MCP Server. Deploy with CData Drivers.

Download MCP Server for free and give your AI tools schema-aware access to live RabbitMQ data during development. When you're ready to move to production, CData RabbitMQ Drivers deliver the same SQL-based access with enterprise-grade performance, security, and reliability.

Visit the CData Community to share insights, ask questions, and explore what's possible with MCP-powered AI workflows.