GHL MCP Server
Enables AI agents to programmatically manage GoHighLevel accounts through a Cloudflare Workers-based server. It currently supports CRUD operations for custom fields, custom values, and object folders with plans to include contact and pipeline management.
README
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
| Tool | Description |
|---|---|
ghl_list_contact_custom_fields |
List all contact custom fields |
ghl_get_contact_custom_field |
Get a specific field by ID |
ghl_create_contact_custom_field |
Create a single field |
ghl_update_contact_custom_field |
Update a field |
ghl_delete_contact_custom_field |
Delete a field |
ghl_bulk_create_contact_custom_fields |
Create multiple fields at once |
Custom Object Fields
| Tool | Description |
|---|---|
ghl_list_object_custom_fields |
List fields for a custom object |
ghl_create_object_custom_field |
Create a field on a custom object |
ghl_create_custom_field_folder |
Create a folder for organizing fields |
Custom Values
| Tool | Description |
|---|---|
ghl_list_custom_values |
List all custom values |
ghl_create_custom_value |
Create a custom value |
ghl_update_custom_value |
Update a custom value |
ghl_delete_custom_value |
Delete a custom value |
Supported Field Types
| Type | Description |
|---|---|
TEXT |
Single-line text |
LARGE_TEXT |
Multi-line text |
NUMERICAL |
Number |
PHONE |
Phone number |
MONETORY |
Currency/money |
EMAIL |
Email address |
DATE |
Date picker |
CHECKBOX |
Checkbox |
SINGLE_OPTIONS |
Dropdown (single select) |
MULTIPLE_OPTIONS |
Multi-select |
RADIO |
Radio buttons |
FILE_UPLOAD |
File attachment |
TEXTBOX_LIST |
List of text inputs |
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
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.