AgentPing

AgentPing

Let your AI agent notify you via email, Slack, Discord, or webhook using a single tool.

Category
访问服务器

README

<p align="center"> <img src="assets/logo-256.png" width="96" alt="AgentPing logo"> </p>

<h1 align="center">AgentPing</h1>

<p align="center"> <b>Let your AI agent notify you — by email, Slack, Discord, or webhook.</b><br> A hosted, remote <a href="https://modelcontextprotocol.io">MCP</a> server. One tool: <code>send_notification</code>. </p>

<p align="center"> <a href="https://ping.mgm-llc.org">Website</a> · <a href="https://ping.mgm-llc.org/docs">Docs</a> · <a href="https://ping.mgm-llc.org/signup">Get an API key (free)</a> </p>


What it does

Long-running agents work while you're away. AgentPing gives them a send_notification tool so they can reach you the moment something matters:

  • ✅ Task done — "Migration finished, 3,412 rows updated."
  • 🙋 Approval needed — "Ready to deploy to prod. Confirm?"
  • 📊 Here's the result — daily summary, scrape output, build status.
  • 🚨 Something broke — error alerts from an autonomous run.

Notifications go to any channel you configure: email, Slack, Discord, or a custom webhook.

🔒 Read-only by design. AgentPing can only send the notifications your agent triggers. It has no access to your inbox, files, or accounts.

Connect it (MCP client config)

A. Remote URL — Cursor and any client that supports Streamable HTTP:

{
  "mcpServers": {
    "agentping": {
      "url": "https://ping.mgm-llc.org/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

B. Stdio bridge — works with every MCP client (incl. Claude Desktop):

{
  "mcpServers": {
    "agentping": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://ping.mgm-llc.org/mcp", "--header", "Authorization: Bearer YOUR_API_KEY"]
    }
  }
}

Get your API key by signing up at ping.mgm-llc.org and setting your destinations. See the full docs for per-client steps and Slack/Discord webhook setup.

Tool

Tool Arguments Notes
send_notification title (string, required), message (string, optional), channel (optional) channel ∈ all | email | slack | discord | webhook. Default: all configured channels.

Pricing

  • Free — 100 notifications/month.
  • Pro — $9/mo or $90/yr — 10,000 notifications/month.

Protocol

Stateless Streamable HTTP (JSON-RPC 2.0): initialize, tools/list, tools/call, ping. Auth via Authorization: Bearer <api_key> (or ?key= for clients that can't set headers).

Self-hosting

Built on Cloudflare Workers + D1 + Hono. To run your own instance:

npm install
npm run db:local
npm run dev            # http://localhost:8787

.dev.vars needs APP_SECRET (and RESEND_API_KEY to enable email).

npx wrangler login
npx wrangler d1 create agentping       # put database_id in wrangler.jsonc
npm run db:remote
npx wrangler secret put APP_SECRET
npx wrangler secret put RESEND_API_KEY
# Stripe billing (optional):
npx wrangler secret put STRIPE_SECRET_KEY
npx wrangler secret put STRIPE_WEBHOOK_SECRET
npx wrangler deploy

Set vars.APP_URL to the production URL and attach a custom domain.

License

MIT · Operated by MGM LLC.

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
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
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
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
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
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
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
mcp-server-qdrant

mcp-server-qdrant

这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。

官方
精选
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选