nannylane-mcp

nannylane-mcp

Unofficial Bun-based MCP server and TypeScript SDK for authenticated Nanny Lane dashboard data, enabling reading dashboard data, searching public nanny listings, inspecting messages, and preparing messages.

Category
访问服务器

README

Nanny Lane MCP

Unofficial Bun-based MCP server and TypeScript SDK for authenticated Nanny Lane dashboard data.

This project lets an MCP client read Nanny Lane dashboard data, search public nanny directory listings, inspect message threads, fetch plan information, and prepare messages through a local server. Authentication is local-only: the server reads a browser Cookie header from environment variables or a private cookie file and never stores credentials in source.

What This Is

  • A local MCP stdio server written in TypeScript and run with Bun.
  • An importable TypeScript SDK for observed Nanny Lane dashboard, GraphQL, Next.js data, listing, plan, and message endpoints.
  • A login helper that can either accept a pasted cookie header or import Nanny Lane cookies from local macOS browsers.
  • A safety-first message tool that defaults to dry-run behavior.

What This Is Not

  • Not an official Nanny Lane integration.
  • Not an OAuth app.
  • Not a credential broker.
  • Not a hosted service.
  • Not a tool that should be run against accounts you do not control.

Documentation

  • Authentication: login helper, browser-cookie import, manual cookie setup, and environment variables.
  • Browser Cookie Import: how Safari and Chrome-family cookie import work.
  • SDK: importable TypeScript SDK entrypoint, client methods, and guardrails.
  • MCP Setup: how to run the server from MCP clients.
  • Tools: complete tool reference with inputs, side effects, and examples.
  • Examples: common MCP tool-call workflows.
  • Architecture: project structure, request flow, and design decisions.
  • Endpoint Map: sanitized map of the Nanny Lane endpoints this server wraps.
  • Troubleshooting: common auth, Cloudflare, browser import, and MCP issues.
  • Development: local checks, repo hygiene, and contribution workflow.
  • Release: release checklist, package verification, and publishing notes.
  • Security: secret handling and side-effect policy.

Quick Start

Install dependencies:

bun install

Authenticate from Safari on macOS:

bun run login:safari

Or authenticate from Chrome:

bun run login:chrome

The login helper validates the session and writes a private cookie file to:

~/.config/nannylane-mcp/cookie

Run the MCP server:

bun run start

Run checks:

bun run check

Run full release checks:

bun run check:release

SDK Usage

import { createNannyLaneClient } from "nannylane-mcp";

const client = createNannyLaneClient();
const nannies = await client.findNannies({
  citySlug: "atlanta",
  stateSlug: "ga",
  first: 10,
});

Useful SDK methods include:

  • findNannies()
  • listingProfile()
  • conversationSummaries()
  • messageThread()
  • sendMessage()
  • plans()
  • upgradeUrl()
  • nextData()
  • graphqlQuery()
  • persistedGraphqlQuery()

See SDK for the complete public entrypoint.

MCP Client Config

From a source checkout, use an absolute path to src/server.ts:

{
  "command": "bun",
  "args": ["/absolute/path/to/nannylane-mcp/src/server.ts"]
}

After package installation, use the shipped bin:

{
  "command": "nannylane-mcp"
}

If you use the default login helper path, no environment variables are required. To use a custom cookie file:

{
  "command": "bun",
  "args": ["/absolute/path/to/nannylane-mcp/src/server.ts"],
  "env": {
    "NANNYLANE_COOKIE_FILE": "/Users/you/.config/nannylane-mcp/cookie"
  }
}

Available Tools

  • nannylane_conversations
  • nannylane_next_data
  • nannylane_dashboard_page_data
  • nannylane_conversations_page_data
  • nannylane_family_profile_page_data
  • nannylane_inbox_summary
  • nannylane_persisted_graphql
  • nannylane_graphql
  • nannylane_peekaboo_bucketing
  • nannylane_directory_page_data
  • nannylane_find_nannies
  • nannylane_listing_profile
  • nannylane_messages
  • nannylane_message_thread
  • nannylane_send_message
  • nannylane_plans
  • nannylane_upgrade_url

See Tools for exact input schemas and behavior.

Example Workflows

Find public nanny listings in Atlanta:

{
  "citySlug": "atlanta",
  "stateSlug": "ga",
  "first": 10
}

Read messages for one listing before deciding whether to send:

{
  "listingId": "listing-id-from-find-nannies"
}

Prepare a message without sending it:

{
  "listingId": "listing-id-from-find-nannies",
  "text": "Hi, I saw your profile and would like to learn more about your availability.",
  "dryRun": true
}

See Examples for complete request/response-style workflows.

Safety Defaults

  • Cookie files are expected outside the repository.
  • .env, .env.*, .cookies/, .tmp/, coverage/, and dist/ are ignored.
  • nannylane_send_message defaults to dryRun: true.
  • The server starts without credentials so MCP clients can list tools before auth is configured.
  • Credential loading is lazy and happens only when a tool call needs to contact Nanny Lane.
  • The release gate verifies both MCP startup and SDK self-import.

Open-Source Hygiene

Before publishing a fork or opening a pull request:

bun run check:release

The release check runs tests, typecheck, Markdown link validation, MCP startup smoke, high-risk secret scanning, and a dry-run package build.

License

MIT. See LICENSE.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选