The MCP Server for kintone integrates your kintone database with AI tools like Claude Desktop through the Model Context Protocol (MCP). This server allows AI assistants to access, query, and manipulate your kintone data, making it possible to interact with your database using natural language.
Download the executable file from the official release page.
You can place the executable file anywhere on your system that's convenient for you.
To configure Claude Desktop to connect with your kintone data:
Locate the Claude Desktop configuration file:
~/Library/Application\ Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
Add the kintone server 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, ..."
}
}
}
}
Configure the following environment variables to connect to your kintone instance:
KINTONE_BASE_URL
: (Required) Your kintone instance URLKINTONE_USERNAME
: Your kintone usernameKINTONE_PASSWORD
: Your kintone passwordKINTONE_API_TOKEN
: Comma-separated list of API tokens
KINTONE_ALLOW_APPS
: Comma-separated list of app IDs to allow access to (default: all apps)KINTONE_DENY_APPS
: Comma-separated list of app IDs to deny access to (overrides allow list)After completing your configuration, restart Claude Desktop to apply the changes.
Once configured, you can interact with your kintone data using natural language through Claude Desktop.
You can ask questions or issue commands like:
The MCP server handles the translation between your natural language queries and the appropriate kintone API calls, allowing you to work with your data conversationally.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.