返回资讯中心
外部精选
软件工程
#开发者实时流

MCP events: who writes the first prompt now?

MCP Events lets a server wake your AI agent when something happens. Here’s what shipped and why it changes security.

Hacker News 最新marcelmarais2026/10/18 · 2026/10/1811 分钟阅读

以下正文同步自 Hacker News 最新,版权归原站所有,已转换为易读排版。

MCP Events lets a server wake your AI agent when something happens. Here’s what shipped and why it changes security.

Remembers the places you visit, privately, on your iPhone.

Every agent starts the same way. A human types something, a cron job fires or that mess of webhooks you built to keep track of external tools delivers something.

MCP Events changes that. It's a draft extension to the Model Context Protocol (SEP-3415) that lets a server tell your agent something happened, like a Slack message, a failed deploy or a comment on a doc, so the agent can act without anyone prompting it.

It's easy to file this under "webhooks for MCP". I think it's a bigger shift than that. For the first time, the first message in an agent run can come from someone other than the user (& effortlessly for the dev building the agent).

Until now MCP has been pull-based. The client calls tools, reads resources and maybe polls a long-running task. If something changed on the server, you found out next time you asked. In my opinion this totally breaks the experience.

The Events draft comes from the Triggers & Events Working Group (Clare Liguori at AWS and Peter Alexander at Anthropic). It adds:

It's pretty well thought through. The webhook section of the design sketch covers SSRF (it checks the resolved IP at delivery time and doesn't follow redirects), endpoint verification before the first delivery, and secret rotation (someone has clearly been burned by webhooks before).

OpenAI announced ChatGPT support at DevDay on 29 September. The Vercel AI SDK added experimental support on 15 October, and Cloudflare's API MCP server now emits Workers issues as events. The reaction on X has been mostly excitement, eg. agents hiring other agents.

That makes sense. Hosted clients have a public HTTPS endpoint, and webhooks are the mode that fits them. Push via events/stream is the mode built for local agents, the ones on your laptop with no public URL, and nobody big ships it. The agents that would gain most from being woken up are the ones that can't be reached.

With pull, the user's prompt always came first. Whatever untrusted text the agent read (an email, an issue, a web page), it read it because someone asked it to, and that someone was usually watching.

With Events, the stranger's text comes first. A GitHub comment or an inbound email wakes the agent, lands in context, and the agent has tools and nobody looking over its shoulder. That's the lethal trifecta (private data + untrusted input + a way to act) with the human taken out of the loop.

The spec's guidance is to treat payloads like tool results and keep them minimal. That's correct, but it feels thin for a run that no human started.

I build Timeline, a location history app for iPhone with an MCP server for agents. Today it's all pull: an agent calls get_current_location or search_visits when you ask it something.

Now imagine it emits visit.started and visit.ended, with a saved place as the subscription argument. That's when it gets kinda magic:

Every one of these ends in a draft or a nudge, not an action. That's the point of the rule above. The agent does the boring 90%, you tap send.

I'm quite bullish. Agents that only wake on a cron job or a chat message are underpowered, and a standard way for servers to push is overdue. The working group's design is careful, and the August roadmap put server-initiated events in its top priority area.

But right now we have one major host, one delivery mode, no SDK support and a spec that's still moving. I'd still build event servers now. Just keep the events thin and assume nobody is watching when they land.

Join the waitlist and we’ll tell you the moment it’s on the App Store.

1,037 people waiting · One email at launch, nothing else.

A draft extension to the Model Context Protocol, proposed in SEP-3415, that lets an MCP server notify a client when something happens upstream. Clients can poll, hold a push stream open, or register a signed webhook.

Not yet. As of October 2026, Claude Code, Cursor and VS Code don't support it. ChatGPT supports the webhook mode in Work chats.

Not yet. SEP-3415 is an open pull request, and the error codes and some details are still provisional.

Remembers the places you visit, privately, on your iPhone.

Upload an export or connect your history so an assistant can answer.

What each option records, where it keeps it, and what it costs.

Save a copy on Android or iPhone, back it up, and read the file.

正文由 探How 从来源站点 RSS 同步,内容未经改写;遇到排版缺失或需要图片、视频时请以原文为准。

打开原文
去社区讨论 →