Agent-Native Analytics MCP Server

io.github.BuilderIO/agent-native-analytics

Connect analytics data sources and generate charts with AI agents using Amplitude/Mixpanel integration.

What is the Agent-Native Analytics MCP server?

Agent-Native Analytics is an MCP server that integrates Amplitude and Mixpanel analytics platforms with AI agents. It enables agents to connect data sources, query analytics data, and generate charts through natural language prompts.

This MCP server bridges analytics platforms (Amplitude/Mixpanel) with AI agents, allowing them to autonomously explore data, answer questions about user behavior, and create visualizations. It's part of the Agent-Native framework, which pairs agent capabilities with purpose-built UIs for knowledge work.

How to install Agent-Native Analytics

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

Tools & capabilities

Tools this server exposes to the agent.

Connect data sources — Connect to Amplitude or Mixpanel analytics accounts
Query analytics data — Execute queries against connected analytics data sources
Generate charts — Create visualizations and charts from analytics data based on agent prompts

Use cases

Ask an AI agent to analyze user engagement trends and automatically generate dashboard charts
Connect multiple analytics sources and have an agent synthesize insights across platforms
Generate on-demand reports by prompting the agent with natural language questions about your data
Build dashboards where an agent autonomously creates visualizations based on business questions
Explore user behavior patterns without manual dashboard navigation

Agent-Native Analytics MCP server FAQ

What is Agent-Native Analytics?

It's an MCP server that connects AI agents to Amplitude and Mixpanel, enabling agents to query analytics data and generate charts through natural language prompts.

How do I install it?

The server is available as a remote streamable-http endpoint at https://analytics.agent-native.com/mcp. Configure it in your MCP client (Cursor, Claude, etc.) to connect to this endpoint.

What analytics platforms does it support?

It integrates with Amplitude and Mixpanel analytics platforms.

Do I need authentication?

Yes, you'll need valid credentials for your Amplitude or Mixpanel account to connect data sources through the MCP server.

Can I use this with Claude or Cursor?

Yes, as an MCP server it works with any MCP-compatible client including Claude and Cursor.

Is it free?

The MCP server itself is part of the open-source Agent-Native framework, but you'll need active Amplitude or Mixpanel subscriptions to use the analytics integrations.

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