@dhuynh95: The #Agent #Plugins standard is out. Will it be a dud? @OpenAI, @cursor_ai, @Google , @vercel and others just released …

X AI KOLs Timeline News
agent-plugins mcp agent-skills open-standard ai-agents vercel openai

Summary

The Agent Plugins standard, backed by OpenAI, Cursor, Google, Vercel, and others, is released as a way to package agent skills with MCP connectors for easy installation on any harness. The author notes it is mostly packaging rather than a breakthrough, but important for agent distribution.

The #Agent #Plugins standard is out. Will it be a dud? @OpenAI, @cursor_ai, @Google , @vercel and others just released a standard way to distribute Agent configuration for an easy install on any harness like #Codex. Interesting note: @AnthropicAI did not participate. An Agent Plugin, from first principles, is packages and ties together Skills (text files with business logic) with their #MCP (connectors). This is quite important as for many use cases coupling the two is needed to have effective Agents Take a plugin for finding LinkedIn leads. “Search leads, then check their profile” isn’t enough. You have to say which tool does it: Google Search, Sales Navigator, etc. So Skills and MCPs go hand in hand. Knowing how to combine them is the “taste” people in SF keep talking about Why it matters: Plugins strengthen this path towards one click installs for Agents. Agents are starting to commoditize more and more, and just like Apps they are starting to have their distribution format and platforms. But will this make Agents 10x better? I don’t think so. It’s mostly packaging, not a breakthrough Until AI engineers think hard about, the right tools, permissions and UX for a specific business problem, no amount of packaging fixes the production blockers we see in most companies
Original Article
View Cached Full Text

Cached at: 08/07/26, 12:51 PM

The #Agent #Plugins standard is out. Will it be a dud?

@OpenAI, @cursor_ai, @Google , @vercel and others just released a standard way to distribute Agent configuration for an easy install on any harness like #Codex. Interesting note: @AnthropicAI did not participate.

An Agent Plugin, from first principles, is packages and ties together Skills (text files with business logic) with their #MCP (connectors). This is quite important as for many use cases coupling the two is needed to have effective Agents

Take a plugin for finding LinkedIn leads. “Search leads, then check their profile” isn’t enough. You have to say which tool does it: Google Search, Sales Navigator, etc.

So Skills and MCPs go hand in hand. Knowing how to combine them is the “taste” people in SF keep talking about

Why it matters: Plugins strengthen this path towards one click installs for Agents. Agents are starting to commoditize more and more, and just like Apps they are starting to have their distribution format and platforms.

But will this make Agents 10x better? I don’t think so. It’s mostly packaging, not a breakthrough

Until AI engineers think hard about, the right tools, permissions and UX for a specific business problem, no amount of packaging fixes the production blockers we see in most companies

Vercel (@vercel): Introducing Agent Plugins, an open standard for extending agents.

Supports Agent Skills and MCP, with more to come.

Built in collaboration with: @awsdevelopers, @code, @cursor_ai, @github, and @openaidevs.

Similar Articles

Agent Plugins (4 minute read)

TLDR AI

Vercel announces Agent Plugins 1.0.0, an open, vendor-neutral standard for packaging Agent Skills and MCP servers into distributable plugins, giving AI agents a common format for discovery and loading.

Agent Plugins are the future of Agent Skills (13 minute read)

TLDR AI

Agent Plugins is a new open, vendor-neutral standard for packaging Agent Skills and their MCP dependencies into one portable folder, with Google joining as a core maintainer. The article details how the standard simplifies distribution, its manifest requirements, and its compatibility across clients.

Introducing Agent Plugins

YouTube AI Channels

AWS, Cursor, GitHub, Microsoft, OpenAI, and Vercel jointly launched Agent Plugins—an open, vendor-neutral packaging format for agent extensions, designed to unify the packaging and discovery of skills and MCP servers, promoting reuse across products.

@mattpocockuk: Oh sweet Expect a mattpocock/skills plugin ASAP

X AI KOLs Timeline

OpenAI announces Agent Plugins, an open standard developed with AWS, Cursor, GitHub, Code, and Vercel to package Agent Skills and support MCP server configurations, enabling plugins to work across compatible agent clients. Matt Pocock reacts enthusiastically and expects a skills plugin soon.