MakeMeBetter AI MCP Server
Connects AI assistants to your MakeMeBetter AI board, enabling natural-language management of tasks, habits, and goals with read/write tools.
README
MakeMeBetter AI — MCP Server
Connect your AI assistant to your MakeMeBetter AI board and manage your tasks, habits, and goals by talking to it.
Ask Claude "what's on my board today?", "push the quarterly report to Friday at 5pm", or "add buy milk under my groceries task" — and it happens on your real board, in the app on your phone.
This repository holds the public metadata and documentation for the hosted MakeMeBetter AI MCP server. The server itself is a managed service — there is nothing to install or self-host.
| Connector URL | https://makemebetter-ai-backend-59998332584.asia-south1.run.app/mcp |
| Transport | Streamable HTTP |
| Auth | OAuth 2.1 — you sign in and approve access; no API keys to copy around |
| Tools | 11 (4 read, 7 write) |
| Cost | Free tier included with every MakeMeBetter AI account |
Getting started
You need a MakeMeBetter AI account. Sign in to the consent screen with the same email as your app account so your assistant lands on your existing board.
Claude (web, desktop, mobile)
Settings → Connectors → Add custom connector → paste the connector URL → sign in → approve. Added once, it works across every Claude surface.
Claude Code
claude mcp add --transport http makemebetter https://makemebetter-ai-backend-59998332584.asia-south1.run.app/mcp
Then complete the OAuth flow in your browser.
ChatGPT
Requires a paid plan (Plus/Pro/Business/Enterprise) and Developer mode (Settings → Apps & Connectors → Advanced settings → Developer mode). The option to add a custom connector only appears once both are true. Then add the connector URL and sign in.
Cursor / VS Code
Add to your editor's MCP config:
{
"mcpServers": {
"makemebetter": {
"url": "https://makemebetter-ai-backend-59998332584.asia-south1.run.app/mcp"
}
}
}
The editor drives the OAuth flow for you.
Tools
Records come back with id, title, status (not_started / in_progress / completed) and
progress_percent, plus due_date, due_time, target_frequency and notes when they're set.
Reading
| Tool | What it does |
|---|---|
list_tasks(include_completed?) |
Your top-level tasks. Active only by default. |
list_habits(include_completed?) |
Your habits, with target_frequency when set. |
list_goals(include_completed?) |
Your longer-term goals. |
get_record(record_id) |
Full detail for one record. For a task, includes its subtasks. |
Writing
| Tool | What it does |
|---|---|
create_task(title, due_date?, due_time?, notes?, parent_task_id?) |
Creates a task, or a subtask when you pass parent_task_id. |
create_habit(title, target_frequency?, notes?) |
target_frequency is free text — "daily", "3x per week". |
create_goal(title, notes?) |
Creates a goal. |
update_record(record_id, ...) |
Partial update — only the fields you pass change. |
set_progress(record_id, percentage) |
Sets progress 0–100. |
complete_record(record_id) |
Marks completed at 100%. |
delete_record(record_id) |
Permanent, and cascades to a task's subtasks. Assistants are instructed to confirm with you first. |
Dates are ISO (2026-07-15); times are 24-hour (17:30) and require a date.
Privacy and security
- Your board only. Every read and write is filtered by your authenticated user id at the database query level. Another user's record id behaves exactly like one that doesn't exist — the server never reveals whether it exists.
- No credentials to hand over. Authentication is OAuth 2.1; your assistant receives a scoped access token, never your password.
- Discovery follows RFC 9728 at
/.well-known/oauth-protected-resource/mcp.
Usage limits
Tool calls are metered per day, per account:
| Plan | Tool calls / day |
|---|---|
| Free | 25 |
| Pro | 2,000 |
initialize and tools/list are free — only actual tool calls count. When you run out, tools
return a plain-language limit notice instead of data, and reset the next UTC day.
Support
Issues and questions: open an issue.
License
The metadata and documentation in this repository are released under the MIT License. The MakeMeBetter AI service itself is a separate, proprietary hosted product.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。