Lets an AI client create and review visual plans with diagrams, wireframes, prototypes, and annotations, then share them.
Also known as BuilderIO/agent-native, agent-native-plan
- Stars
- 7,696
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.0
- Last commit
- Nov 13, 2026
- License
- MIT
What is Agent-Native Plans MCP?
Agent-Native Plans lets an AI client create and review visual plans with diagrams, wireframes, prototypes, and annotations, then share them.
Summary generated from the project's README
About Agent-Native Plans MCP server
Developers building autonomous agents with dedicated user interfaces can use this TypeScript framework to bridge the gap between AI actions and visual feedback. It allows an agent to perform work through shared actions that are accessible via the UI, HTTP, MCP, or a command line interface. By using a unified action layer, the agent and the human user interact with the same validation and implementation logic.
The system provides a structured environment where agents can receive relevant application state, such as the active view or a selected record. It includes built-in support for authentication, permissions, and persistent memory. For data management, it utilizes a PostgreSQL backend for production environments and PGlite for local development. This setup ensures that work performed by an AI is immediately visible and editable within the application interface.
What you can do with it
- 1Visual UI editingAsk an AI client to modify a running application interface using a canvas instead of text prompts.
- 2Creating visual plansGenerate and inspect diagrams, wireframes, and prototypes through a dedicated planning application.
- 3Synchronized agent and UI workEnsure that any changes made by an agent are reflected in the interface and vice versa.
Written from the project's README. Every use case is checked against a quote from it.
How to install Agent-Native Plans MCP
Formats verified 10 Nov 2026Install Agent-Native Plans MCP in Claude Code
$ claude mcp add --transport http agent-native-plan https://plan.agent-native.com/mcpInstall Agent-Native Plans MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agent-native-plan": {
"url": "https://plan.agent-native.com/mcp"
}
}
}Install Agent-Native Plans MCP in VS Code
.vscode/mcp.json
{
"servers": {
"agent-native-plan": {
"type": "http",
"url": "https://plan.agent-native.com/mcp"
}
}
}Install Agent-Native Plans MCP in Codex
~/.codex/config.toml
[mcp_servers.agent-native-plan] url = "https://plan.agent-native.com/mcp"
Install Agent-Native Plans MCP in Gemini CLI
~/.gemini/settings.json
{
"mcpServers": {
"agent-native-plan": {
"httpUrl": "https://plan.agent-native.com/mcp"
}
}
}Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packageNot checked
- Remote endpoint uses HTTPSPass
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesNot checked
README
View on GitHubAgent-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
Open-source agents
Start from one of these agents or use it as an example for your own. For a source-to-answer architecture example, see Brain’s visual overview.
Clips
Record and understand meetings, screens, and voice notes.
Design
Generate and refine interactive designs.
Slides
Create and edit on-brand presentations.
Analytics
Ask questions of your data and build dashboards.
Calendar
Find time, schedule events, and manage bookings.
Prioritize email, draft replies, and follow up.
Assets
Create and organize on-brand media.
Content
Draft, organize, and publish content.
Plans
Create and review visual plans with diagrams, wireframes, and prototypes.
Explore the full app gallery, or start with the framework guide.
Documentation and community
- Read the documentation.
- Join Discord to ask questions, share what you're building, and get help.
Contributing
Want to send a change back? Start with CONTRIBUTING.md. DEVELOPMENT.md covers local setup, workspace structure, and guard scripts.
License
MIT
Agent-Native Plans MCP questions
How do I add Agent-Native Plans MCP to Claude Code?
Run claude mcp add --transport http agent-native-plan https://plan.agent-native.com/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Agent-Native Plans MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What can I create with Agent-Native Plans?
You can create and review visual plans that include diagrams, wireframes, and prototypes, with annotations and sharing.
Can I edit a running app visually instead of prompting each change?
Yes, the /visual-edit skill in Claude Code lets you edit a running app on a canvas, compare live pages, and have the chosen edits applied to source.
Does the agent interact with the UI by clicking?
No, the agent works through the same shared action layer as the UI rather than clicking through it.
How are capabilities exposed to the agent?
Each capability is defined once as an action, which the agent uses as a tool and the UI calls from code, and it is also exposed through HTTP, MCP, A2A, and the CLI.