MCP.so
Sign In
C

CSV Files MCP Server by CData

@CDataSoftware

Basic information

Category

Data & Analytics

Transports

stdio

Author

CDataSoftware

Submitted by

Cameron Leblanc

About CSV Files MCP Server by CData

This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free [CData MCP Server for CSV Files (beta)](https://www.cdata.com/download/download.aspx?sku=RVZK-V&type=beta).

CSV Files MCP Server by CData config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "{classname_dash}": {
      "command": "PATH\\TO\\java.exe",
      "args": [
        "-jar",
        "PATH\\TO\\CDataMCP-jar-with-dependencies.jar",
        "PATH\\TO\\csv-files.prp"
      ]
    }
  }
}

CSV Files MCP Server by CData tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is CSV Files MCP Server by CData?

A read-only MCP (Model Context Protocol) server that lets LLMs like Claude Desktop query live CSV files using natural language. It wraps the CData JDBC Driver for CSV Files, exposing local CSV data as relational SQL tables without requiring SQL knowledge from the user.

How to use CSV Files MCP Server by CData?

Clone the repository, build the JAR with mvn clean install, download and license the CData JDBC Driver for CSV Files, and create a .prp configuration file with the JDBC connection string. Then configure your MCP client (e.g., Claude Desktop) to launch the server with java -jar CDataMCP-jar-with-dependencies.jar <path-to>.prp. The server uses the stdio transport and runs locally.

Key features of CSV Files MCP Server by CData

  • Read-only MCP server for querying CSV data.
  • Exposes CSV files as relational SQL models.
  • Supports natural language queries via MCP interface.
  • Built-in tools: get_tables, get_columns, run_query.
  • Requires CData JDBC Driver for CSV Files.
  • Uses stdio transport for local client communication.

Use cases of CSV Files MCP Server by CData

  • Ask an LLM to summarize sales figures from CSV invoices.
  • Query CSV log files for trends and anomalies.
  • Retrieve filtered records from CSV datasets without writing SQL.
  • Analyze relationships across multiple CSV tables through natural language.

Frequently asked questions

1

Is this server read-only?

Yes, it is a read-only MCP server. For full read, write, update, and delete capabilities, use CData’s free MCP Server for CSV Files (beta).

2

What transport does the server use?

It uses stdio, so the server must run on the same machine as the MCP client (e.g., Claude Desktop).

3

What are the runtime requirements?

Java (to run the JAR), Maven (to build from source), and the CData JDBC Driver for CSV Files (requires a free trial or license key).

4

How do I configure the connection?

Create a `.prp` file with properties such as `JdbcUrl`, `DriverPath`, `DriverClass`, and `Tables`. Use the connection string builder provided by the JDBC driver to generate the correct URL.

Comments

More Data & Analytics MCP servers