🧠 GHL MCP Server – Anthropic LangGraph Agent Integration

Name: 🧠 GHL MCP Server – Anthropic LangGraph Agent Integration
Author: JewelreyBoxAI

@JewelreyBoxAI

代码仓库

关于 🧠 GHL MCP Server – Anthropic LangGraph Agent Integration

GHL MCP server to GHL Demo Sub Account

#mathgpt #math-solver #math-assistant

基本信息

分类

AI 与智能体

运行时

python

传输方式

stdio

发布者

JewelreyBoxAI

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "MCP-GHL": {
      "command": "python",
      "args": [
        "scripts/start_server.py"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is 🧠 GHL MCP Server – Anthropic LangGraph Agent Integration?

This server exposes GoHighLevel (GHL) sub-account tools to an Anthropic-powered LangGraph agent using the Model Context Protocol (MCP). It acts as a secure intermediary between the LangChain ecosystem and GHL APIs, designed for clean modular separation and zero-handoff latency.

How to use 🧠 GHL MCP Server – Anthropic LangGraph Agent Integration?

Create a .env file with your GHL API key, sub-account ID, and base URL. Install dependencies with pip install -r requirements.txt. Start the server using uvicorn mcp_server:app --host 0.0.0.0 --port 8000 or the startup script. Test connection with python examples/simple_client.py or run interactive mode.

Key features of 🧠 GHL MCP Server – Anthropic LangGraph Agent Integration

FastAPI MCP server exposing GHL sub-account tools
Dynamic tool registration via LangChain MCP adapters
Secure credential loading through .env variables
Pre-built tools for contacts, pipelines, and automations
Supports Claude-based LangGraph Agents as MCP clients
Zero-coupling between agent and GHL API

Use cases of 🧠 GHL MCP Server – Anthropic LangGraph Agent Integration

A Claude-powered agent retrieves contact details from GHL in real time
Automates pipeline and opportunity updates without manual login
Triggers custom workflows by calling webhook endpoints
Creates notes on contacts based on user conversation context
Enables LangGraph agents to manage GHL sub-accounts programmatically

FAQ from 🧠 GHL MCP Server – Anthropic LangGraph Agent Integration

What is the purpose of this server?

It acts as a secure intermediary between LangChain agents and GoHighLevel APIs, exposing GHL tools (contacts, pipelines, automations) to Claude-based LangGraph agents via MCP.

What environment variables are required?

You need GHL_API_BASE_URL, GHL_API_KEY, GHL_SUB_ACCOUNT_ID, and optionally ALLOWED_ORIGINS. All are set in a .env file at the root of ghl_mcp_server/.

Where can I find the GHL credentials?

GHL_API_KEY: GHL Settings → API Keys
GHL_SUB_ACCOUNT_ID: URL bar while inside the sub-account dashboard
Webhook/Funnel/Contact IDs: found in respective page URLs or contact details

What are the runtime dependencies?

Python 3.11+, FastAPI, and the langchain-mcp-adapters package. Optionally NGROK or Azure App Service for public MCP endpoint exposure.

How do tools communicate with the agent?

All tool usage is routed over HTTP via LangChain’s MCP standard. The server exposes endpoints that the MCP client calls using MCPClient.load_tools(). No data leaves the user’s GHL sub-account except through authorized API calls.

AI 与智能体分类下的更多 MCP 服务器

21st.dev Magic AI Agent

21st-dev

It's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic

5.3K

欢迎来到智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797