Neuron MCP Server

Neuron MCP Server

Enables AI assistants to manage WhatsApp business operations including chatbots, broadcasts, campaigns, and contacts through 120+ MCP tools.

Category
Visit Server

README

Neuron MCP Server

WhatsApp automation platform with 120+ MCP tools for AI-powered chatbots, broadcasts, campaigns, and more.

npm version License: MIT

What is Neuron?

Neuron is an AI-powered WhatsApp automation platform. This MCP server exposes 120+ tools that let AI coding assistants — Claude Code, Cursor, Windsurf, and other MCP-compatible clients — manage your entire WhatsApp business programmatically.

Build chatbots, send broadcasts, manage contacts, create campaigns, publish newsletters, and more — all through natural language with your AI assistant.

Quick Start

Option 1: Remote Server (Recommended — zero install)

Add to your MCP client config:

{
  "mcpServers": {
    "neuron": {
      "type": "url",
      "url": "https://mcp.neuron.ng/mcp"
    }
  }
}

No installation required. Works immediately with any MCP client that supports Streamable HTTP.

Option 2: Local Server (via npm)

Run directly with npx:

npx neuron-mcp-server

Or install globally:

npm install -g neuron-mcp-server

Claude Code config (~/.claude/mcp.json):

{
  "mcpServers": {
    "neuron": {
      "command": "npx",
      "args": ["-y", "neuron-mcp-server"]
    }
  }
}

Authentication

Three ways to authenticate:

1. Browser Login (Recommended)

Call neuron_login() with no arguments. The server returns a URL — open it in your browser to authorize securely. No credentials are shared with the AI.

2. MCP Token

Generate a token from your Neuron dashboard (Settings > MCP Tokens), then:

neuron_login({ token: "your-mcp-token" })

3. Environment Variable

Set NEURON_AUTH_TOKEN for unattended/CI use:

NEURON_AUTH_TOKEN=your-token npx neuron-mcp-server

Available Tools (120+)

Category Tools Description
Authentication 8 Login, register, org switching, profile management
Bot Management 7 Create and manage AI chatbots with configurable LLM models
Conversations 11 Message management, human takeover, send WhatsApp messages
Knowledge Bases 14 Upload documents, semantic search, sync, ingest content
Contacts 12 CRUD operations, import/export, semantic search, sync
Contact Lists 11 Segmentation, merge, membership management
Channels 17 WhatsApp connections, QR pairing, session management
Broadcasts 7 Bulk messaging to contact lists
Campaigns 14 Sponsored campaigns, marketplace, funding
Newsletters 8 WhatsApp Channel/newsletter management
Webhooks 8 Inbound and outbound webhook management
Custom Tools 6 HTTP API tools for bots with secret injection
Blog 6 Content publishing
Organizations 7 Team management, audit logs, member invitations
Billing & Wallet 12 Subscriptions, wallet, payouts, bank accounts
Marketplace 8 Publish and install bots and contact lists
Reflections 4 Self-learning bot improvement suggestions
Media & AI 2 Upload media, AI text rewriting

Environment Variables

Variable Description Default
NEURON_API_URL API base URL https://api.neuron.ng/api/v1
NEURON_AUTH_TOKEN Pre-set auth token —
MCP_TRANSPORT Transport mode: stdio or http stdio
PORT HTTP server port (when using http transport) 3001

IDE Setup

Claude Code

Add to ~/.claude/mcp.json:

{
  "mcpServers": {
    "neuron": {
      "command": "npx",
      "args": ["-y", "neuron-mcp-server"]
    }
  }
}

Or use the remote server:

{
  "mcpServers": {
    "neuron": {
      "type": "url",
      "url": "https://mcp.neuron.ng/mcp"
    }
  }
}

Cursor

Settings > MCP Servers > Add Streamable HTTP

URL: https://mcp.neuron.ng/mcp

Windsurf

Settings > AI > MCP Servers > Add

Use either the remote URL or local npx command.

Development

git clone https://github.com/conquext/neuron-mcp-server.git
cd neuron-mcp-server
npm install
npm run dev

Links

Free to start — no credit card required.

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured