--- title: "Agent Plugins package your skills, tools, and more" url: https://daily.dev/posts/agent-plugins-package-your-skills-tools-and-more-fo0qucyro source_url: https://developers.googleblog.com/agent-plugins-package-your-skills-tools-and-more type: article source: "Google Developers" published: 2026-08-06T16:09:48.421Z updated: 2026-08-07T03:53:25.941Z tags: ["ai-agents", "mcp"] reading_time: 5 upvotes: 0 comments: 0 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Agent Plugins package your skills, tools, and more **[Google Developers](https://daily.dev/sources/googledevs)** · 5 min read · 0 upvotes · 0 comments ## Summary Agent Plugins 1.0.0 is a vendor-neutral open specification for packaging Agent Skills and MCP servers into portable, interoperable plugins. Maintained by a TSC including Amazon, Cursor, Microsoft, OpenAI, and Vercel — with Google now joining as a Core Maintainer — it solves the problem of incompatible manifest formats across AI clients. A plugin is simply a directory with a minimal plugin.json, a skills/ folder, and an optional mcp.json. The spec deliberately omits install mechanisms, distribution protocols, and permission models, leaving those to individual clients. Google's Agents CLI and Data Agent Kit are the first Google products to adopt the format, with more planned. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is the Agent Plugins 1.0.0 specification and what problem does it solve? Agent Plugins 1.0.0 is an open, vendor-neutral specification for packaging Agent Skills and MCP servers into a portable directory format. It solves the problem of incompatible manifest layouts across AI clients — where the same skill and MCP server required forked packages with different directory structures and metadata shapes for each client. The spec defines a minimal plugin.json, a fixed skills/ directory, and an mcp.json for MCP server declarations. _Developers shipping agent tools across multiple clients track packaging standards like this on daily.dev._ ### What does an Agent Plugins directory structure look like and what files are required? An Agent Plugins directory requires only a plugin.json manifest with a $schema reference and a name field. Skills live under skills/, one subdirectory per skill in Agent Skills format. MCP servers are declared in mcp.json with an explicit transport type (stdio, Streamable HTTP, or legacy HTTP+SSE). A reverse-domain directory like com.example.client/ is the extension namespace for client-specific additions that other clients safely ignore. _Teams standardizing their agent packaging workflows find the latest ecosystem moves on daily.dev._ ### Which companies are core maintainers of the Agent Plugins specification? The Agent Plugins specification is maintained by a TSC with Core Maintainers from Amazon, Cursor, Microsoft, OpenAI, and Vercel. Google joined as a Core Maintainer, represented by Kevin Hou, and is integrating the format into its own products — starting with Agents CLI and Data Agent Kit, which connects to BigQuery, Spanner, and Cloud SQL. _Keeping up with which companies back emerging AI tooling standards matters when choosing what to build on — daily.dev covers those moves._ --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#mcp](https://daily.dev/tags/mcp) [View this post on daily.dev](https://daily.dev/posts/agent-plugins-package-your-skills-tools-and-more-fo0qucyro)