Kintone Integration MCP Server

Customer Data PlatformsGo

Access and manipulate Kintone data using AI tools

Available Tools

list_apps

Lists available Kintone applications

get_app

Gets information about a specific Kintone application

list_records

Lists records from a Kintone application

get_record

Gets a specific record from a Kintone application

add_record

Adds a new record to a Kintone application

update_record

Updates an existing record in a Kintone application

delete_record

Deletes a record from a Kintone application

The Kintone Integration MCP server enables AI tools like Claude Desktop to interact with your Kintone database. This integration allows you to query, explore, and manipulate data stored in Kintone applications through natural language conversations with AI assistants. With this MCP server, you can ask questions about your Kintone data, request updates to records, and analyze information across multiple Kintone applications. It bridges the gap between powerful AI capabilities and your business data stored in Kintone.

Overview

The Kintone Integration MCP server allows AI tools like Claude Desktop to connect with your Kintone database, enabling natural language interactions with your business data. This integration makes it possible to query, analyze, and update Kintone records through conversational AI interfaces.

Installation

Download the latest release from the GitHub release page.
Save the executable file to a location on your computer.

Configuration

To use the Kintone Integration with Claude Desktop or other MCP-compatible AI tools, you'll need to configure the client to connect to the MCP server.

Claude Desktop Configuration

Edit the Claude Desktop configuration file located at:

MacOS/Linux: ~/Library/Application\ Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the following configuration to the mcpServers section:

{
  "mcpServers": {
    "kintone": {
      "command": "C:\\path\\to\\mcp-server-kintone.exe",
      "env": {
        "KINTONE_BASE_URL": "https://<domain>.cybozu.com",
        "KINTONE_USERNAME": "<your username>",
        "KINTONE_PASSWORD": "<your password>",
        "KINTONE_API_TOKEN": "<your api token>, <another api token>, ...",
        "KINTONE_ALLOW_APPS": "1, 2, 3, ...",
        "KINTONE_DENY_APPS": "4, 5, ..."
      }
    }
  }
}

Environment Variables

Configure the following environment variables to connect to your Kintone instance:

KINTONE_BASE_URL (Required): The base URL of your Kintone instance (e.g., https://your-domain.cybozu.com).
KINTONE_USERNAME: Your Kintone username.
KINTONE_PASSWORD: Your Kintone password.
KINTONE_API_TOKEN: Comma-separated list of API tokens for Kintone.
- Note: You must set either username/password or API token(s).
KINTONE_ALLOW_APPS: Comma-separated list of app IDs to allow access to. By default, all apps are allowed.
KINTONE_DENY_APPS: Comma-separated list of app IDs to deny access to. Deny rules have higher priority than allow rules.

After configuring, restart your AI client (e.g., Claude Desktop) to apply the changes.

Usage Examples

Once configured, you can interact with your Kintone data using natural language. Here are some example prompts you can use with Claude Desktop:

"What is the latest status of Customer A's project?"
"Update the progress of Project B to 50%."
"Show me the projects that are behind schedule."
"List all customers in the Tokyo region."
"Create a new task for the marketing team with a deadline of next Friday."

The AI will interpret these requests and use the MCP server to fetch or update the relevant data in your Kintone instance.