Kadai
Client-shared issue tracker where AI agents read issues, comment and mark resolved
- Pricing
- Free trial
- Platforms
- Web, API
- Runs
- Remotely
- Version
- 1.0.0
- Listing updated
- 1 day ago
About Kadai
Kadai is an MCP server for productivity. It runs as a hosted remote server, so there is nothing to install locally.
Kadai is a Japanese-language issue tracker built for agencies and teams that work with clients. The MCP connection lets an AI agent such as Claude Code list projects and issues, read one, comment, change its state and check notifications addressed to the user. After a person confirms, it can also add issues and documents.
The guardrail is that an AI can only move an issue to 'processed'; marking it 'complete' stays with a human. Comments and changes made by AI carry an AI mark and appear in the change history. Tokens are issued per space and can be read-only, and each project can opt out of AI access so it disappears from the agent's list.
Pricing is 500 yen per person per month before tax, counting admins and members but not clients. Spaces started before 31 March 2027 are free until that date, and later ones get a 30-day trial. Payment is by invoice and bank transfer. The site lists missing features such as SSO, audit logs, webhooks and a mobile app.
Install
Run in a terminal
claude mcp add --transport http kadai https://kadai.work/mcpAdd to Settings → Connectors → Add custom connector
https://kadai.work/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"kadai": {
"url": "https://kadai.work/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"kadai": {
"type": "http",
"url": "https://kadai.work/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"kadai": {
"serverUrl": "https://kadai.work/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"kadai": {
"type": "http",
"url": "https://kadai.work/mcp"
}
}
}What it does
- Issue reading and comments
- Agents list and read issues and write progress reports as comments.
- Processed, not complete
- AI can set 'processed' but only a person can mark an issue complete.
- AI marks in history
- AI-written comments and changes are labelled and logged.
- Scoped tokens
- Tokens are issued per space and can be read-only.
- Per-project opt-out
- Projects with AI turned off are hidden from the agent.
- Drafting helpers
- Procedures exist for starting work, drafting issues from text, summaries, translation and weekly reports.
Good for
- Have a coding agent pick up an issue and report back in the comments
- Draft new issues from meeting notes after a person confirms
- Generate a weekly progress report from issue activity
- Keep a client-facing project off-limits to AI
Pricing
Free trial
500 yen per person per month before tax; 30-day trial; invoice and bank transfer.
Prices change. Check kadai.work before you buy.
Kadai FAQ
What does it cost?
500 yen per person per month before tax (550 with tax), with clients free to invite.
Can the AI close an issue?
No. It can set 'processed' only; a person marks it complete.
Is there a free trial?
Spaces started by 31 March 2027 are free until then; later spaces get a 30-day trial with no card.
Which AI tools work?
Any tool that supports MCP over HTTP; the settings page shows a Claude Code command.
Is Kadai free?
Kadai is a paid product with a free trial.
How do I add Kadai to Claude Code?
Run this command in your terminal: claude mcp add --transport http kadai https://kadai.work/mcp
What are the best alternatives to Kadai?
The closest alternatives to Kadai are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to Kadai

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ha MCP
MCP serverMCP server for managing and automating Home Assistant from AI assistants
Runs locally- 8 tools
- Open source
- 7.9K GitHub stars
- Productivity