MCP.so
登录

Nestling

@kparmesar

代码仓库

关于 Nestling

Nestling is an MCP server that lets you log and query your baby's daily routine. Feeds, sleep, nappy changes, and diary entries through natural conversation with Claude or any MCP-compatible AI assistant. Logged through the Nestling app for iOS and Android.

基本信息

分类

AI 与智能体

传输方式

stdio

发布者

kparmesar

提交者

Kevon Parmesar

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "nestling": {
      "command": "bun",
      "args": [
        "run",
        "nestling-mcp"
      ],
      "cwd": "/absolute/path/to/nestling-ts",
      "env": {
        "NESTLING_API_TOKEN": "your-token-from-nestling-app",
        "NESTLING_TIMEZONE": "Europe/London"
      }
    }
  }
}

工具

12

Discovery: what data sources and tools are available

Account profile (email, user ID)

Baby roster (`id` is passed to every other tool)

Baby details (nickname, birth date, etc.)

Sleep sessions for a baby in a date range

Feeding entries (breast, bottle, solids) in a date range

Nappy/diaper entries in a date range

Diary/journal entries in a date range

Log a new sleep session (start + end time)

Log a new feed (breast, bottle, solids, expressing)

Log a new nappy/diaper change

Log a new diary/journal entry

概览

What is Nestling?

Nestling is a TypeScript client, CLI, and MCP server for the Nestling baby tracking app. It reads and logs sleep, feed, nappy, and diary data from your Nestling account via terminal, library, or AI assistants like Claude and ChatGPT.

How to use Nestling?

Install globally with bun add -g nestling-ts, then run nestling login to authenticate and use CLI commands like nestling sleep history. For MCP integration, point Claude or ChatGPT at the nestling-mcp binary (stdio or HTTP mode). The library is imported as import { Nestling } from "nestling-ts".

Key features of Nestling

  • CLI and library for reading and logging baby data
  • MCP server for AI assistants (Claude, ChatGPT, etc.)
  • Create-only writes – cannot update or delete entries
  • Supports sleep, feed, nappy, and diary entries
  • HTTP or stdio transport for MCP
  • User-scoped authentication with Supabase Row Level Security

Use cases of Nestling

  • Log a sleep session from the terminal: nestling sleep log --start "yesterday 8pm" --end "today 6:30am"
  • Query feeding history for the last two days: nestling feed history --days 2
  • Let an AI assistant read and log baby data via MCP tools
  • Automate baby tracking with scripts using the TypeScript library
  • Self-host a remote MCP endpoint for multiple users

FAQ from Nestling

What does Nestling do that the Nestling app cannot?

Nestling provides a programmatic interface (CLI, library, MCP) to read and log data, but it is create-only — it cannot update or delete existing entries.

What are the dependencies to run Nestling?

Bun 1.3+ (the package is raw TypeScript, not Node-compatible), a Nestling account, and an API token generated from the app (Settings → Data → API Token).

Where does my data live when using the MCP server?

In stdio mode, credentials stay on your machine. In HTTP mode, you can self-host or use the hosted endpoint (https://mcp.nestling-app.com/mcp). All data is stored in Supabase with Row Level Security per user.

What transport modes does the MCP server support?

Two modes: stdio (default, for local tools like Claude Desktop) and HTTP (for remote clients like ChatGPT custom connectors).

How is authentication handled?

Authentication uses an API token passed via environment variable (NESTLING_API_TOKEN) or config file. The token is used to bootstrap a short-lived Supabase session (auto-refreshed after 1 hour). No service keys are used.

评论

AI 与智能体 分类下的更多 MCP 服务器

1MCP - One MCP Server for All

1mcp-app

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

468

🛡️ A.I.G（AI-Infra-Guard）

Tencent

A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

4.1K

Solon Ai

opensolon

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

416

MCP Server - Remote MacOs Use

baryhuang

The only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App

487

MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages

utensils

MCP-NixOS - Model Context Protocol Server for NixOS resources

739