Agent-Native Assets MCP Server

io.github.BuilderIO/agent-native-assets

Digital asset manager for agents—upload, organize, search, and generate on-brand images and videos

What is the Agent-Native Assets MCP server?

Agent-Native Assets is a digital asset management MCP server that enables agents to upload, organize, search, and generate on-brand images and videos. It integrates with the Agent-Native framework to provide shared asset actions accessible to both AI agents and UI applications.

Agent-Native Assets is a component of the Agent-Native framework that manages digital media. It allows agents to handle image and video assets programmatically while keeping the same asset library synchronized with a UI interface. Use it to automate asset organization, enable agents to generate on-brand creative content, and maintain a centralized media repository accessible across agent and human workflows.

How to install Agent-Native Assets

Copy-paste configuration for popular MCP clients.

transport: http

Config generated by PluginBench — verify against the source before use.

~/.cursor/mcp.json

{
  "mcpServers": {
    "agent-native-assets": {
      "url": "https://assets.agent-native.com/mcp"
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

Upload assets — Upload images and videos to the asset library
Organize assets — Organize and manage digital assets in collections
Search assets — Search for images and videos in the asset library
Generate assets — Generate on-brand images and videos

Use cases

Automate bulk upload and organization of brand assets for design and marketing workflows
Enable agents to search and retrieve on-brand images when creating presentations, designs, or content
Generate new on-brand images and videos programmatically for marketing campaigns or social media
Maintain a synchronized asset library accessible to both AI agents and human team members through a shared UI
Delegate asset curation and generation tasks to agents while maintaining brand consistency

Agent-Native Assets MCP server FAQ

What is Agent-Native Assets?

Agent-Native Assets is an MCP server that provides digital asset management capabilities—upload, organize, search, and generate images and videos—integrated into the Agent-Native framework so agents can manage media programmatically.

Is Agent-Native Assets free?

Agent-Native is open-source under the MIT license, so the framework and Assets app are free to use and modify.

How do I connect Agent-Native Assets to Claude or Cursor?

Agent-Native Assets is available as a remote MCP server at https://assets.agent-native.com/mcp. Add it to your Claude or Cursor MCP configuration to enable asset management capabilities.

What authentication is required?

The README does not specify authentication requirements. Check the Agent-Native documentation or contact the community on Discord for details on auth setup.

Can agents and the UI share the same assets?

Yes. Agent-Native Assets uses shared actions—the same asset operations work for both agents and the UI, keeping asset libraries synchronized across both interfaces.

What types of media does it support?

Agent-Native Assets handles images and videos. It supports uploading, organizing, searching, and generating on-brand visual content.

README (reference)

Source of truth, from the repository.

Agent-Native

Agent-Native is an open-source TypeScript framework for building agents that pair autonomous work with a purpose-built UI. Define each capability once as an action: the agent uses it as a tool, and the UI calls it from code.

Quick start

npx --yes @agent-native/core@latest create my-agent --standalone --template chat

Follow the getting started guide for a full intro to the framework.

Why build agents with UIs?

Coding agents work with more than a text box. Their environment provides context, tools, files, tests, and previews that make their capabilities and results visible.

Knowledge work needs that same kind of environment. A UI shows what an agent can do and gives people familiar ways to inspect, edit, approve, and share its work.

How Agent-Native works

Shared actions. The agent calls each capability as a tool, and the UI calls it from code. Both paths use the same validation, permissions, and implementation.
Shared data. Work done by the agent appears in the UI, and work done in the UI is available to the agent.
Shared application state. The agent receives relevant UI state, such as the current page, selected record, or active view.

The agent does not click through the UI. It works through the same action layer as the UI.

Example: a shared action

Create actions/hello.ts:

import { defineAction } from "@agent-native/core/action";
import { z } from "zod";

// One action powers every app surface: UI, agent, HTTP, MCP, A2A, and CLI.
export default defineAction({
  description: "Return a friendly greeting.",
  schema: z.object({
    name: z.string().default("world").describe("Name to greet"),
  }),
  http: { method: "GET" },
  run: async ({ name }) => {
    return { message: `Hello, ${name}!` };
  },
});

The agent receives hello as a tool. React calls the same function with useActionQuery("hello", { name: "Alex" }). Agent-Native also exposes it through HTTP, MCP, A2A, and the CLI.

Included

Agent chat: Let people delegate work, ask questions, and review results in the same UI.
Authentication and permissions: Control who can access and change shared work.
Skills and memory: Give agents reusable expertise and persistent context.
Automations: Run agent work on schedules or events.
Agent teams: Delegate work to specialist agents in the same workspace or across connected agents.
PostgreSQL backend: Use PostgreSQL in production and PGlite for local development on any Nitro-compatible host.

Example: edit a running app visually

Use /visual-edit in Claude Code to edit a running app on a canvas instead of prompting for each small UI nudge. Compare live pages together, then ask Claude to apply the chosen edits to your source. For example:

/visual-edit the onboarding flow, plus home at every breakpoint

Review the onboarding screens alongside Home at desktop, tablet, and mobile sizes, adjust a button's color or spacing directly, then ask Claude to apply the pending edits to your source. See the Visual Edit guide for the full walkthrough and sharing details.

Bring your LLM, SQL database, tools, and infrastructure. Everything you build stays yours.

See Agent-Native in action:

https://github.com/user-attachments/assets/ef51644b-6506-46d8-8083-0af7b7e5b65c