How to Access Live CSV 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 Code Assist MCP for CSV, 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 Code Assist MCP 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 Code Assist MCP for CSV on WSL (Windows Subsystem for Linux) and connect to it from the Cline extension in Visual Studio Code on Windows.

Background

Code Assist MCP 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 Code Assist MCP for CSV installed on Windows

Step 1: Authenticate with CSV (on Windows)

Before running Code Assist MCP 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 Code Assist MCP for CSV" or execute the JAR file to open the configuration wizard.

java -jar "C:\Program Files\CData\CData Code Assist MCP for CSV 20XX\lib\cdata.mcp.csv.jar"

Connecting to CSV

Connecting to Local or Cloud-Stored (Box, Google Drive, Amazon S3, SharePoint) CSV Files

CData Drivers let you work with CSV files stored locally and stored in cloud storage services like Box, Amazon S3, Google Drive, or SharePoint, right where they are.

Setting connection properties for local files

Set the URI property to local folder path.

Setting connection properties for files stored in Amazon S3

To connect to CSV file(s) within Amazon S3, set the URI property to the URI of the Bucket and Folder where the intended CSV files exist. In addition, at least set these properties:

• AWSAccessKey: AWS Access Key (username)
• AWSSecretKey: AWS Secret Key

Setting connection properties for files stored in Box

To connect to CSV file(s) within Box, set the URI property to the URI of the folder that includes the intended CSV file(s). Use the OAuth authentication method to connect to Box.

Dropbox

To connect to CSV file(s) within Dropbox, set the URI proprerty to the URI of the folder that includes the intended CSV file(s). Use the OAuth authentication method to connect to Dropbox. Either User Account or Service Account can be used to authenticate.

SharePoint Online (SOAP)

To connect to CSV file(s) within SharePoint with SOAP Schema, set the URI proprerty to the URI of the document library that includes the intended CSV file. Set User, Password, and StorageBaseURL.

SharePoint Online REST

To connect to CSV file(s) within SharePoint with REST Schema, set the URI proprerty to the URI of the document library that includes the intended CSV file. StorageBaseURL is optional. If not set, the driver will use the root drive. OAuth is used to authenticate.

Google Drive

To connect to CSV file(s) within Google Drive, set the URI property to the URI of the folder that includes the intended CSV file(s). Use the OAuth authentication method to connect and set InitiateOAuth to GETANDREFRESH.

Configuring Code Assist MCP

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

👁 The Code Assist MCP configuration wizard (Google Sheets is shown).

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

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

Step 2: Copy the Code Assist MCP 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/"csv Provider" ~/.config/CData/

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

Step 3: Install Code Assist MCP on WSL

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

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

Step 4: Configure Cline

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

Create or update cline_mcp_settings.json with the following content:

{
 "mcpServers": {
 "cdatacsv": {
 "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_csv/lib/cdata.mcp.csv.jar",
 "cdatacsv"
 ],
 "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.

cdatacsv_get_tables
cdatacsv_get_columns Customer

If configured correctly, these commands will return a list of available CSV 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 CSV Lead."
• "Write a Python function to pull Opportunities closed this quarter."

Build with Code Assist MCP. Deploy with CData Drivers.

Download Code Assist MCP for free and give your AI tools schema-aware access to live CSV data during development. When you're ready to move to production, CData CSV 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.