Get the FREE Ultimate OpenClaw Setup Guide →

kintone -by-cdata

This read-only MCP Server allows you to connect to Kintone 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
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio cdatasoftware-kintone-mcp-server-by-cdata java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/kintone.prp

How to use

This MCP server provides a read-only interface to Kintone data via the CData JDBC Driver. It wraps the JDBC driver for Kintone and exposes the data through the MCP protocol so large language models can query live data without writing SQL themselves. The server is intended for local use and operates in stdio mode, meaningClients on the same machine can interact with it via the configured config entry. The available tools include: kintone_get_tables to list all accessible tables, kintone_get_columns to list columns for a specific table, and kintone_run_query to execute a SQL SELECT query against the underlying data. You typically configure Claude Desktop (or another MCP client) with a .prp/claude config that points to the Java JAR and the .prp file, then run the server and query with natural language questions; the client translates those into calls to the exposed tools.

How to install

Prerequisites:

  • Java Runtime Environment (JRE) or JDK installed on the host machine
  • Maven (for building the MCP server JAR) if you need to build from source
  • CData JDBC Driver for Kintone installed and licensed on the host where the JAR will run

Installation steps:

  1. Clone the repository and build the MCP server (if starting from source): git clone https://github.com/cdatasoftware/kintone-mcp-server-by-cdata.git cd kintone-mcp-server-by-cdata mvn clean install

    This produces CDataMCP-jar-with-dependencies.jar

  2. Install the CData JDBC Driver for Kintone:

  3. License the JDBC Driver (one-time):

    • Navigate to the lib folder of the installation (examples): Windows: C:\Program Files\CData\CData JDBC Driver for Kintone
      Mac/Linux: /Applications/CData JDBC Driver for Kintone/
    • Run: java -jar cdata.jdbc.kintone.jar --license
    • Enter your name, email, and a license key (or TRIAL)
  4. Create a .prp connection profile for your JDBC data source (example steps):

    • Use the provided sample in the README to craft kintone.prp, including fields like Prefix, ServerName, ServerVersion, DriverPath, DriverClass, JdbcUrl, Tables
    • Example content is shown in the README under the kintone.prp section
  5. Run the MCP server using the JAR and the .prp file: java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/Salesforce.prp Note: The server runs with stdio and is intended for local use.

  6. Configure your MCP client (e.g., Claude Desktop) with the generated configuration to expose kintone_by_cdata as an MCP server entry.

Additional notes

Tips and notes:

  • The MCP server described here is read-only; write/update/delete capabilities are not exposed. Use it to query live Kintone data via natural language prompts.
  • The server communicates over stdio, which constrains clients to run on the same machine.
  • Ensure the kintone.prp is correctly configured with the JDBC URL and proper DriverPath and DriverClass values.
  • If Claude Desktop or your MCP client doesn’t show the server, fully quit and re-open the client, or re-load the configuration file as described in the README.
  • If you encounter connection issues, verify that the JDBC driver is licensed and that the connection string in kintone.prp is valid, then re-test via the driver’s connection utility.
  • The available tools follow a naming convention: {servername}_get_tables, {servername}_get_columns, {servername}_run_query. Replace {servername} with the configured class name (e.g., kintone_by_cdata).
  • For Windows vs Linux/macOS, ensure the command and paths in your Claude config align with the host OS conventions.
  • The README contains JSON-RPC examples for scripting tool calls; use those payloads to automate interactions if needed.

Related MCP Servers

Sponsor this space

Reach thousands of developers