GHL MCP Server

A remote MCP (Model Context Protocol) server running on Cloudflare Workers that gives AI agents full programmatic access to GoHighLevel.

What This Does

Your AI agents connect to this server as a tool. They can then create, read, update, and delete custom fields, custom values, and custom field folders in your GHL account — no manual work required.

Current capabilities (Phase 1):

• Contact-level custom fields (full CRUD + bulk create)

• Custom object fields (Custom Objects + Company)

• Custom field folders

• Custom values (location-wide variables)

Planned (Phase 2+):

• Contacts management

• Opportunities & Pipelines

• Calendars & Appointments

• Conversations & Messaging

• Workflows

• And every other GHL API endpoint

Architecture

Your AI Agent (Claude, GPT, etc.)
        │
        │  MCP Protocol (Streamable HTTP)
        ▼
┌─────────────────────────┐
│  Cloudflare Worker       │
│  (GHL MCP Server)        │
│                          │
│  ┌────────────────────┐  │
│  │  McpAgent          │  │  ← Durable Object (stateful sessions)
│  │  (tools defined)   │  │
│  └────────┬───────────┘  │
│           │              │
│  ┌────────▼───────────┐  │
│  │  GHL API Client    │  │  ← Typed HTTP client
│  └────────┬───────────┘  │
└───────────┼──────────────┘
            │
            │  REST API (Bearer token)
            ▼
┌─────────────────────────┐
│  GoHighLevel API         │
│  services.leadconnector  │
│  hq.com                  │
└─────────────────────────┘

Setup

Prerequisites

• Node.js 18+

• A Cloudflare account

• A GoHighLevel Private Integration Token

• Your GHL Location ID (Sub-Account ID)

1. Clone & Install

git clone https://github.com/YOUR_USERNAME/ghl-mcp-server.git
cd ghl-mcp-server
npm install

2. Configure Secrets

For local development, copy the example env file:

cp .dev.vars.example .dev.vars
# Edit .dev.vars with your actual GHL credentials

For production deployment, set secrets via Wrangler:

npx wrangler secret put GHL_API_KEY
npx wrangler secret put GHL_LOCATION_ID

3. Deploy

npm run deploy

Your MCP server will be live at: https://ghl-mcp-server.YOUR_SUBDOMAIN.workers.dev/sse

4. Connect Your AI Agent

Use the deployed URL as an MCP server endpoint in your AI agent's configuration.

For Claude Desktop (via mcp-remote proxy):

{
  "mcpServers": {
    "ghl": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://ghl-mcp-server.YOUR_SUBDOMAIN.workers.dev/sse"
      ]
    }
  }
}

Available Tools

Contact-Level Custom Fields

Custom Object Fields

Custom Values

Supported Field Types

Roadmap

Phase 2: Contacts

• Create, update, delete, search contacts

• Bulk contact operations

• Tag management

• Notes and tasks

Phase 3: Opportunities & Pipelines

• Pipeline management

• Opportunity CRUD

• Stage updates

Phase 4: Calendars & Conversations

• Calendar management

• Appointment scheduling

• Send messages (SMS, email)

Phase 5: Workflows & Automation

• Trigger workflows

• Manage workflow configurations

Phase 6: Everything Else

• Forms, Surveys, Funnels

• Payments, Invoices, Products

• Media library

• Social media posting

Development

# Local development
npm run dev

# Deploy to production
npm run deploy

GHL API Reference

This server is built against the GoHighLevel API V2. The OpenAPI specs from the official docs repo are included in /api-specs for reference.

License

MIT