@zeph-to/mcp-server

@zeph-to/mcp-server

MCP server for AI agents to send notifications, copy to clipboard, request confirmations, and collect text input from users across their devices.

Category
访问服务器

README

@zeph-to/mcp-server

Zeph MCP server for AI agents. Send notifications, copy to clipboard, request confirmations, and collect text input from users across their devices — all via the Model Context Protocol.

Setup

The easiest way to set up for all agents at once:

npx @zeph-to/hook-sdk install

This saves credentials to ~/.zeph/config.json and configures your agents automatically. The MCP server reads from this file — no env vars needed.

Claude Code (manual)

Add to ~/.claude/settings.json:

{
  "mcpServers": {
    "zeph": {
      "command": "npx",
      "args": ["-y", "@zeph-to/mcp-server"],
      "env": {
        "ZEPH_API_KEY": "ak_...",
        "ZEPH_HOOK_ID": "hook_...",
        "ZEPH_DEVICE_ID": "dev_..."
      }
    }
  }
}

Cursor / Other MCP Clients

{
  "command": "npx",
  "args": ["-y", "@zeph-to/mcp-server"],
  "env": {
    "ZEPH_API_KEY": "ak_..."
  }
}

Environment Variables

Variable Required Description
ZEPH_API_KEY Yes API key from Settings > API Keys
ZEPH_HOOK_ID No Hook ID for interactive tools (zeph_prompt, zeph_input)
ZEPH_DEVICE_ID No Target device ID. Omit to send to all devices
ZEPH_BASE_URL No API base URL (default: https://api.zeph.to/v1)

Tools

zeph_notify

Send a one-way push notification. Supports optional URL (auto-switches to link type).

title:          "Build complete"
body:           "All 42 tests passed"
url:            "https://github.com/org/repo/actions/runs/123"  (optional)
priority:       "low" | "normal" | "high" | "urgent"
targetDeviceId: "dev_..."  (optional, overrides ZEPH_DEVICE_ID)

zeph_clipboard

Copy text to the user's device clipboard.

text:           "npm install @zeph-to/mcp-server"
targetDeviceId: "dev_..."  (optional)

zeph_list

List recent push notifications.

limit: 5         (1-20, default: 5)
type:  "note"    (optional filter: note, link, file, clipboard, hook)

Returns: { pushes: [...], total: 5, hasMore: true }

zeph_dismiss

Mark a specific push as read.

pushId: "push_01HX..."

zeph_dismiss_all

Clear all notifications at once. No parameters.

Returns: { dismissed: 12, badge: 0 }

zeph_broadcast

Send a notification to all subscribers of a channel.

channelId: "ch_..."
title:     "Deploy complete"
body:      "v2.1.0 is live"
url:       "https://..."  (optional)
priority:  "normal"

zeph_file

Send a text file to the user's device.

fileName:       "report.json"
content:        "{\"status\": \"ok\"}"
title:          "Build Report"  (optional, defaults to fileName)
targetDeviceId: "dev_..."       (optional)

Returns: { pushId: "...", fileKey: "...", fileSize: 42 }

zeph_prompt

Ask the user to choose from 2-4 options. Blocks until response or timeout.

Requires ZEPH_HOOK_ID.

title:    "Deploy to production?"
body:     "3 migrations pending"
actions:  [{ id: "yes", label: "Deploy", style: "primary" },
           { id: "no",  label: "Cancel", style: "danger" }]
timeout:  120        (seconds, default: 120, max: 300)
fallback: "no"       (auto-select on timeout, optional)

Returns: { actionId: "yes", timedOut: false }

zeph_input

Request free-form text input from the user. Blocks until response or timeout.

Requires ZEPH_HOOK_ID.

title:       "Commit message"
body:        "Summarize the changes"
placeholder: "feat: ..."
inputType:   "text" | "password" | "multiline"
timeout:     120    (seconds, default: 120, max: 600)

Returns: { value: "feat: add clipboard sync", timedOut: false }

Resources

zeph://devices

Lists connected devices with online status. Use to check which devices will receive notifications.

zeph://channels

Lists channels the user owns or subscribes to. Use to find channelId for zeph_broadcast.

Usage Guide

When to use each tool

Situation Tool Example
Long task finished zeph_notify Build complete, test results, deploy done
Need user decision zeph_prompt Choose deploy target, confirm destructive action
Need free-form input zeph_input Commit message, env var value, description
Share code/logs zeph_file Error logs, test reports, generated config
Share snippet zeph_clipboard API key, URL, shell command

Recommended patterns

Task completion notification:

zeph_notify(
  title: "Build complete: web app",
  body: "All 42 tests passed. Bundle size: 1.2MB (-3%)"
)

Decision gate in CI/deploy flow:

zeph_prompt(
  title: "Deploy to production?",
  body: "3 migrations pending. Last deploy: 2h ago.",
  actions: [
    { id: "deploy", label: "Deploy", style: "primary" },
    { id: "staging", label: "Staging only", style: "secondary" },
    { id: "cancel", label: "Cancel", style: "danger" }
  ],
  fallback: "cancel"
)

Collecting user input remotely:

zeph_input(
  title: "Commit message",
  body: "Changed: hooks.ts, input.ts, prompt.ts",
  placeholder: "feat: ..."
)

Error alert with link:

zeph_notify(
  title: "CI failed: lint errors",
  body: "2 errors in src/auth.ts",
  url: "https://github.com/org/repo/actions/runs/456",
  priority: "high"
)

When NOT to use

  • Short responses the user can see immediately in the terminal
  • Read-only operations (file search, code analysis)
  • Every single tool call — only notify on meaningful milestones

Multi-session workflow

When running multiple AI agent sessions in parallel, use zeph_notify to signal completion so the user knows which session finished without checking each terminal.

API Key Permissions

The API key needs the following scopes:

  • push:read — for zeph_list
  • push:write — for zeph_notify, zeph_clipboard, zeph_dismiss, zeph_dismiss_all, zeph_file
  • hook:write — for zeph_prompt and zeph_input
  • channel:read — for zeph://channels resource

Create an API key with the MCP preset in Settings > API Keys for the correct permissions.

License

Apache-2.0

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