home / mcp / excel online mcp server

Excel Online MCP Server

This read-only MCP Server allows you to connect to Excel Online data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cdatasoftware-excel-online-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/excel-online.prp"
      ]
    }
  }
}

This MCP server wraps the CData JDBC Driver for Excel Online and exposes live Excel Online data through a simple, read-only MCP interface. It lets you ask natural language questions and retrieve up-to-date information from Excel Online without writing SQL, enabling AI assistants to query your data securely and efficiently.

How to use

You connect to this server from an MCP-enabled client or AI assistant. After the server is running on your machine, your client will discover the MCP server as a local, read-only data source. You can then ask questions like “What is the status of open opportunities in my sheet?” or “Show me the latest calendar events for today,” and the AI will translate your request into read-only data queries against Excel Online. You do not need to know SQL to use it; simply pose natural language questions and rely on the built-in tools to fetch relevant tables, columns, and query results.

How to install

Prerequisites: you need Java installed on your machine and Maven for building the server. Ensure Java Runtime Environment (JRE) or JDK is available in your system PATH.

1. Clone the project and navigate into the directory.

git clone https://github.com/cdatasoftware/excel-online-mcp-server-by-cdata.git
cd excel-online-mcp-server-by-cdata

2. Build the server to produce the MCP JAR with dependencies.

mvn clean install

3. Install the CData JDBC Driver for Excel Online from the CData site and license it following the on-screen prompts in your driver installation. Then locate the DriverPath and DriverClass you will use for the JDBC connection configuration.

4. Create a JDBC connection property file (for example, excel-online.prp) using the required fields: Prefix, ServerName, ServerVersion, DriverPath, DriverClass, JdbcUrl, and Tables. This file defines how the MCP server will connect to your Excel Online data.

5. Run the MCP server using the final startup command shown in the server’s run instruction.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/Salesforce.prp

Additional content

Configuration notes: the MCP server runs locally on your machine and uses stdio for client communication, so the client must run on the same host. The server exposes the Excel Online data through a simple MCP interface and requires a properly created .prp file that includes the JDBC connection string and table definitions.

Usage patterns: after starting the server, you can query the data by asking questions like “How many open tickets do I have in the SUPPORT project?” or “What is the correlation between closed opportunities and account industry?” The built-in tools will present tables and columns to help guide your questions.

Troubleshooting tips: ensure the Claude Desktop or your MCP client is fully restarted after adding or updating the MCP server configuration so the server becomes visible. Verify the JDBC connection string in the .prp file and re-test the connection if data retrieval fails. If you encounter issues with data access or tool execution, contact CData Support or the CData Community for assistance.

License and sources

This MCP server is provided under the MIT License. It enables you to connect to Excel Online data through the CData JDBC Driver and expose it via the MCP interface for read-only access.

Available tools

excel_online_get_tables

Retrieves a list of tables available in the data source. The output is CSV with a header row of column names.

excel_online_get_columns

Retrieves a list of columns for a specific table. The output is CSV with a header row of column names.

excel_online_run_query

Executes a SQL SELECT query against the data source and returns the results.