GHL MCP Server
Enables Claude to manage GoHighLevel CRM contacts, pipelines, and workflows through natural language commands.
README
GHL MCP Server — No Pressure Power Washing
MCP server that connects Claude.ai to GoHighLevel CRM. Manage contacts, pipelines, and workflows by typing natural language messages in Claude.
Tools Available
| Tool | What it does |
|---|---|
ghl_create_contact |
Create a new contact |
ghl_search_contacts |
Search by name, email, or phone |
ghl_get_contact |
Get full contact details by ID |
ghl_list_pipelines |
List all pipelines and stage IDs |
ghl_list_workflows |
List all workflow IDs and names |
ghl_get_opportunities |
Get pipeline opportunities for a contact |
ghl_move_pipeline_stage |
Move an opportunity to a new stage |
ghl_trigger_workflow |
Trigger a workflow for a contact |
Deploy to Railway
Step 1 — Create GitHub repo
Push this folder to a new GitHub repo named nppw-ghl-mcp.
Step 2 — Create Railway project
- Go to railway.app and sign in
- Click New Project → Deploy from GitHub repo
- Connect your GitHub account if prompted
- Select the
nppw-ghl-mcprepo - Click Deploy Now
Step 3 — Set environment variables
In Railway, go to your service → Variables tab → Add Variable:
| Variable | Value |
|---|---|
GHL_API_KEY |
pit-6dc5107a-2bff-4415-922b-16d1c7f570b0 |
GHL_LOCATION_ID |
NUrUflrnfVcqSxE0nrHl |
TRANSPORT |
http |
Railway automatically sets PORT.
Step 4 — Generate a public domain
- In Railway, go to your service → Settings → Networking
- Click Generate Domain
- You'll get a URL like
https://nppw-ghl-mcp.up.railway.app
Step 5 — Connect to Claude.ai
- Open claude.ai → Settings → Integrations
- Click Add Integration
- Enter your Railway URL +
/mcp:https://nppw-ghl-mcp.up.railway.app/mcp - Name it GHL Manager → Save
That's it. Claude can now manage your GHL account from any device.
Local Development
# Install dependencies
npm install
# Create .env file
echo "GHL_API_KEY=your_key" > .env
echo "GHL_LOCATION_ID=your_location_id" >> .env
echo "TRANSPORT=http" >> .env
# Run in dev mode
npm run dev
# Build
npm run build
npm start
Example Usage in Claude.ai
"Add new lead: Sarah Johnson, 919-555-0000, sarah@gmail.com, tagged as residential"
"Find Michael Green and tell me what pipeline stage he's in"
"Move opportunity ID xyz to the Booked stage"
"Trigger the post-job follow-up workflow for contact abc123"
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。