🧠 GHL MCP Server – Anthropic LangGraph Agent Integration

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

@JewelreyBoxAI

Repository

About 🧠 GHL MCP Server – Anthropic LangGraph Agent Integration

GHL MCP server to GHL Demo Sub Account

#mathgpt #math-solver #math-assistant

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

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

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

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.

Comments

More AI & Agents MCP servers

Solon Ai

opensolon

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

416

1Panel

1Panel-dev

🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.

36.1K

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