Kadai
Issue tracker shared with clients (Japanese UI): read issues, comment, move them to resolved.
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
claude mcp add --transport http kadai 'https://kadai.work/mcp' --header 'Authorization: <Bearer <token>. Issue a token in Kadai: 設定 > AI 連携(MCP) (per space, can be read-only).>'
{
"mcpServers": {
"kadai": {
"type": "http",
"url": "https://kadai.work/mcp",
"headers": {
"Authorization": "<Bearer <token>. Issue a token in Kadai: 設定 > AI 連携(MCP) (per space, can be read-only).>"
}
}
}
}
Frequently asked questions
What is Kadai?
Issue tracker shared with clients (Japanese UI): read issues, comment, move them to resolved.
How do I install Kadai?
It runs as a remote server. In Claude Code: claude mcp add --transport http kadai 'https://kadai.work/mcp' --header 'Authorization: <Bearer <token>. Issue a token in Kadai: 設定 > AI 連携(MCP) (per space, can be read-only).>'. For other clients, paste the JSON configuration from this page into their MCP settings.
Does Kadai need an API key?
Yes. It expects Authorization, which you set in its configuration.
Who maintains Kadai?
It is published by work.kadai. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.