home / mcp / smartsheet mcp server

Smartsheet MCP Server

This read-only MCP Server allows you to connect to Smartsheet 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-smartsheet-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/smartsheet.prp"
      ]
    }
  }
}

You can query Smartsheet data live using a local, read-only MCP server that exposes Smartsheet via the CData JDBC Driver. This lets you ask natural language questions and retrieve up-to-date information without writing SQL, while keeping the data access self-contained on your machine.

How to use

After you start the MCP server, you interact with it through an MCP client. The server runs locally and presents a simple set of tools you can invoke to inspect and query your Smartsheet data. You don’t need to write SQL queries directly; you simply ask questions about your data and the client uses the exposed tools to fetch results. Typical usage includes listing available tables, inspecting columns for a table, and running queries to retrieve specific rows.

How to install

# Prerequisites
- Java JRE/JDK (for running the MCP server)
- A local environment where you can run the MCP JAR and the JDBC driver

# 1. Clone the project and enter the folder
git clone https://github.com/cdatasoftware/smartsheet-mcp-server-by-cdata.git
cd smartsheet-mcp-server-by-cdata

# 2. Build the server to produce the JAR with dependencies
mvn clean install

# 3. Install the CData JDBC Driver for Smartsheet (follow the driver’s installer steps on your platform)
# (Download link is provided by the driver vendor and is not part of this script)

# 4. License the CData JDBC Driver
# Windows example
# Navigate to the driver install folder, then run:
java -jar cdata.jdbc.smartsheet.jar --license
# Enter your name, email, and TRIAL (or your license key)

# 5. Configure the JDBC connection
# Run the connection string utility to build and test a connection, then copy the connection string
java -jar cdata.jdbc.smartsheet.jar
# Use the utility to configure and test, then copy the JDBC URL

# 6. Create a .prp file for the JDBC connection
# Name: smartsheet.prp
# Content (example values shown as placeholders):
Prefix=smartsheet
ServerName=CDataSmartsheet
ServerVersion=1.0
DriverPath=PATH\TO\cdata.jdbc.smartsheet.jar
DriverClass=cdata.jdbc.smartsheet.SmartsheetDriver
JdbcUrl=jdbc:smartsheet:InitiateOAuth=GETANDREFRESH;
Tables=

# 7. Run the MCP server with the prepared .prp file
# Linux/Mac/Windows syntax shown; ensure paths are correct for your environment
java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/smartsheet.prp
```
  }]} ,{

Additional sections

Configuration and runtime behavior are designed to be straightforward. The server uses a stdio interface, meaning it runs locally on the same machine as your client and communicates via standard input/output streams. The setup steps cover licensing, connection setup, and starting the MCP server so you can begin querying Smartsheet data right away.

Security and access considerations: Since this is a local, read-only MCP server, you control the machine and environment. If you plan to enable broader access, you would need to migrate to a remote MCP platform or implement your own secure proxy, as this local variant emphasizes simplicity and immediate data visibility for LLMs.

Available tools

smartsheet_get_tables

Retrieves a list of tables available in the Smartsheet data source. The output is provided in CSV format with a header row describing the columns.

smartsheet_get_columns

Retrieves a list of columns for a specified table. The output is provided in CSV format with a header row describing the columns.

smartsheet_run_query

Executes a SQL SELECT query against the Smartsheet data source and returns matching rows.