Agent Plugins 1.0.0: Google Joins Standard to Package Agent Skills and MCP Servers

ArticleKevin Hou, Haoyu Wang, Alan BlountAnnouncement

Google has joined the Technical Steering Committee of Agent Plugins. The vendor-neutral 1.0.0 specification standardises how Agent Skills and MCP servers are packaged within a portable directory structure across multiple AI clients.

Key points

  1. Agent Plugins 1.0.0 is an open specification led by core maintainers from Amazon, Cursor, Microsoft, OpenAI, Vercel, and Google.
  2. A plugin uses a fixed directory structure: a minimal plugin.json manifest, a skills/ folder, and an mcp.json file for declaring transports explicitly.
  3. Components fail independently: an error in an MCP server does not prevent the client from loading functional skills.
  4. Client-specific hooks or configurations are accommodated via reverse-domain folders and ignored by incompatible clients.
  5. The spec intentionally omits installation pipelines, sandboxing, permission systems, and UX, focusing strictly on packaging.
  6. Google provides initial support in Agents CLI and Data Agent Kit to connect tools like BigQuery, Spanner, and Cloud SQL to compatible clients.

Why it matters

Developers previously had to maintain separate wrapper manifests and directory structures for identical skills and MCP servers across different clients. A shared packaging specification eliminates duplicate maintenance and divergence across coding assistants such as Cursor, Claude Code, and Gemini CLI.

Analysis

The Agent Plugins initiative deliberately limits its scope to avoid over-engineering. By leaving installation protocols, execution sandboxing, and UI workflows to the individual clients, version 1.0.0 remains a lightweight packaging convention. Decoupling discovery (Agentic Resource Discovery), indexing (AI Catalog), packaging (Agent Plugins), and execution (MCP and Agent Skills) allows development teams to adopt individual layers without platform lock-in.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Article:Eric Dodds, Andrew Qu

    Agent Plugins 1.0: Open Standard for Packaging AI Agent Extensions

    Agent Plugins 1.0.0 has been launched as a vendor-neutral standard to package Agent Skills and MCP servers into portable plugins. The initiative was spearheaded by Vercel in collaboration with AWS, Microsoft, OpenAI, and Anysphere.

    AI & LLMs· Announcement

  • Article:Libby Clark und James Ward

    AWS Backs Agent Plugins: Open Standard for Portable Agent Extensions

    Agent Plugins 1.0.0 introduces a vendor-neutral open-source specification for packaging AI agent extensions. AWS joins Cursor, Microsoft, OpenAI, and Vercel on the Technical Steering Committee to drive unified cross-client portability.

    AI & LLMs· Announcement

  • Video

    Video:The AI Automators

    Agent Plugins: New Open Standard for AI Agent Extensions

    Industry players including Google, Vercel, and AWS are backing the new 'Agent Plugins' open specification. The standard packages Agent Skills and MCP servers into a unified folder structure, allowing extensions to work across multiple coding agents like Codex, Cursor, VS Code, and GitHub Copilot. Anthropic is currently not participating, though conversion tools exist.

    AI & LLMs· Tutorial

  • Link:agent-plugins.org

    Agent Plugins Specification 1.0.0 Released

    The Agent Plugins Specification 1.0.0 establishes a normative standard for portable plugin packages that extend AI agent runtimes with modular components.

    AI & LLMs· Resource

  • Repository:agentplugins/agent-plugins-example

    Agent Plugins Example: Reference Package for Portable AI Agent Extensions

    The agentplugins/agent-plugins-example repository provides a canonical reference package and migration guide for the Agent Plugins Specification v1.0.0. It demonstrates how to structure portable manifests and skills while cleanly isolating client-specific extensions.

    64stars

    AI & LLMs· Resource

  • Link:Anthropic

    Agent Skills: An Open Standard for Modular AI Agent Capabilities

    Agent Skills is an open format designed to equip AI agents with specialised domain knowledge and repeatable workflows. Centred around a directory containing a SKILL.md file, it relies on progressive disclosure to keep context overhead minimal.

    AI & LLMs· Resource

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.