GHL

Connect Claude-like agents to GoHighLevel via MCP to read, create, and manage data across GoHighLevel APIs.
  • typescript

0

GitHub Stars

typescript

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

You can connect GoHighLevel data and actions to AI-powered workflows via this MCP server. It exposes sub-account GoHighLevel API endpoints through Model Context Protocol, enabling you to automate contacts, messages, calendars, opportunities, billing, and more with machine-assisted context and orchestration.

How to use

You interact with the MCP server from an MCP client (such as Claude Desktop) or a web-based client. Start by ensuring your MCP server is running, your Private Integrations API key is configured, and your Location ID is set. From your client, request tools and capabilities exposed by the server, then issue commands to read data, create or update records, or trigger automations. The server supports a wide range of operations across contacts, messaging, calendars, opportunities, invoices, products, payments, blogs, and more. Use your client to perform actions in the GoHighLevel account and let the MCP layer coordinate the appropriate API calls behind the scenes.

Typical usage patterns include finding specific records (for example, contacts with particular tags), initiating communications (SMS or email), scheduling or rescheduling appointments, updating opportunities, and generating reports from invoices and payments. You can combine multiple steps into a single workflow, such as locating VIP contacts, sending personalized messages, and scheduling follow-up meetings based on calendar availability.

How to install

Prerequisites you need before installing: Node.js 18+ (Latest LTS recommended), a GoHighLevel account with API access, a valid Private Integrations API key, and a Location ID. You will also benefit from Claude Desktop or another MCP client to interact with the server.

Step-by-step installation and setup instructions:

  1. Clone the project repository
  2. Install dependencies
  3. Create and configure the environment file
  4. Build the project
  5. Start the server
  6. Validate health and available tools with test requests

Additional sections

MCP Configuration for Claude Desktop is provided as a ready-to-use example. You direct the MCP server by specifying the node runtime and the path to the compiled server, along with the required environment variables.

{
  "mcpServers": {
    "ghl_mcp": {
      "command": "node",
      "args": ["path/to/ghl-mcp-server/dist/server.js"],
      "env": {
        "GHL_API_KEY": "your_private_integrations_api_key",
        "GHL_BASE_URL": "https://services.leadconnectorhq.com",
        "GHL_LOCATION_ID": "your_location_id"
      }
    }
  }
}

Security, best practices & troubleshooting

Secure your credentials by storing API keys in environment variables and never committing them to version control. Enable proper rate limiting, logging, and monitoring. Use HTTPS for all deployments and implement access controls for your MCP clients.

If you encounter issues, verify: the Private Integrations key is used (not a regular API key), the required scopes are enabled, the Location ID matches your GHL account, and environment variables are properly set. For Claude Desktop integration, ensure the MCP configuration syntax is correct and the server path is absolute.

Testing & health checks

Test connectivity and tool availability from your MCP client or via simple HTTP checks against the server endpoints. Check health, list available tools, and verify the event-stream endpoint if you are using SSE.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
GHL MCP Server - thinkbedo/gohighlevel_mcp | VeilStrat