Agent-Native Mail MCP Server

io.github.BuilderIO/agent-native-mail

AI-powered email client with keyboard shortcuts and intelligent message triage

What is the Agent-Native Mail MCP server?

Agent-Native Mail is an email client built on the Agent-Native framework that combines AI-driven email triage with keyboard shortcuts for efficient inbox management. It enables agents to prioritize emails, draft replies, and manage follow-ups through shared actions that work both in the UI and as MCP tools.

Agent-Native Mail provides an agentic email experience where AI assists with inbox prioritization, reply drafting, and follow-up management. It's part of the Agent-Native ecosystem, meaning the same email actions work through the UI, agent tools, HTTP, MCP, and CLI—giving you flexibility in how you interact with your email.

How to install Agent-Native Mail

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

Tools & capabilities

Tools this server exposes to the agent.

Email triage — AI-powered prioritization and categorization of incoming emails
Draft replies — Generate and refine email responses with AI assistance
Follow-up management — Track and manage email follow-ups

Use cases

Automatically prioritize and triage incoming emails to focus on what matters most
Draft professional email replies with AI assistance and refinement
Manage follow-ups and ensure important emails don't slip through the cracks
Use keyboard shortcuts for fast email navigation and actions
Delegate email management tasks to an AI agent while maintaining UI control

Agent-Native Mail MCP server FAQ

What is Agent-Native Mail?

Agent-Native Mail is an AI-powered email client that combines intelligent message triage, reply drafting, and follow-up management. It's built on the Agent-Native framework, so the same actions work in the UI, as agent tools, and through MCP.

Is Agent-Native Mail free?

Agent-Native is open-source (MIT license), so the framework and Mail app are free. You bring your own LLM, database, and infrastructure.

How do I use it with Claude or Cursor?

Connect the MCP server at https://mail.agent-native.com/mcp to Claude or Cursor. The server exposes email actions (triage, draft, follow-up) as tools the agent can call.

What authentication is required?

Agent-Native Mail requires email account credentials to access your mailbox. Authentication and permissions are managed through the Agent-Native framework's built-in auth system.

Can I run this locally?

Yes. Agent-Native is open-source and self-hosted. You can run it locally with PGlite for development or PostgreSQL for production on any Nitro-compatible host.

What email providers does it support?

The README does not specify which email providers are supported. Check the Agent-Native documentation or repository for provider compatibility details.

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