该寄存器演示了如何使用两个MCP服务器来构建代理工作流程,以检测并逆向配置漂移于一个梅拉基网络. 该系统利用:

• 探测网络变化的Splunk MCP代理。 * Credit to William Searle for the Sprunk MCP Server.* 向威廉·西尔(英语:William Searle)推荐Sprunk MCP服务器.
• 一个梅拉基MCP代理 扭转未经授权的改变。

代理AI处理基于自然语言提示的探测和补救——不需要硬码的管弦.

– – . . .

∮ 如何运作∮

1. 你问: " 我的梅拉基网络有什么变化? "
2. Splunk MCP Agent 使用SDK查询斯普伦克并返回配置漂移。
3. 梅拉基MCP代理将变化与真相来源进行比较,并称适当的梅拉基API可以逆转.

– – . . .

□□ 先决条件

• Python 3.10 或 更高级
• 访问:
• 有相关日志的斯普伦克实例
• 一个梅拉基Dashboard API键
• Claude桌面或任何MCP兼容客户端
• claude_desktop_config.json 配置有正确的工具注册和MCP服务器路径

– – . . .

□ 安装

** 清除储存库:**

Splunk MCP 设置( 本地安装) 用于更多 Splunk MCP 安装选项检查: https://github.

🧠 Self-Healing Network with MCP Agents

This repository demonstrates how to build agentic workflows using two MCP servers to detect and reverse configuration drift in a Meraki network. The system utilizes:

• A Splunk MCP Agent to detect network changes. Credit to William Searle for the Splunk MCP Server.
• A Meraki MCP Agent to reverse unauthorized changes.

Agentic AI handles both detection and remediation based on natural language prompts—no hardcoded orchestration required.

---

🚀 How It Works

1. You ask: “What changed in my Meraki network?”
2. The Splunk MCP Agent queries Splunk using its SDK and returns configuration drift.
3. The Meraki MCP Agent compares the change to the source of truth and calls the appropriate Meraki API to reverse it.

---

🛠️ Prerequisites

• Python 3.10 or higher
• Access to:
  • A Splunk instance with relevant logs
  • A Meraki Dashboard API key
  • Claude Desktop or any MCP-compatible client
• claude_desktop_config.json configured with correct tool registration and MCP server paths

---

📦 Installation

Clone the repository:

git clone https://github.com/kiskander/mcp-splunk-meraki.git
cd mcp-splunk-meraki

Splunk MCP Setup (Local Installation)

for more Splunk MCP installation options checkout: https://github.com/livehybrid/splunk-mcp

1. Access Splunk MCP:

   cd mcp-splunk-meraki/SplunkMCP
   

2. Install dependencies using Poetry:

   poetry install
   

3. Configure environment variables:

   Copy the example environment file and update it with your Splunk credentials:

   cp .env.example .env
   

   Update the .env file with the following:

   SPLUNK_HOST=your_splunk_host
   SPLUNK_PORT=8089
   SPLUNK_USERNAME=your_username
   SPLUNK_PASSWORD=your_password
   SPLUNK_SCHEME=https
   VERIFY_SSL=true
   FASTMCP_LOG_LEVEL=INFO
   SERVER_MODE=stdio
   

4. Run the Splunk MCP:

   poetry run python splunk_mcp.py stdio
   

---

Meraki MCP Setup

1. Install uv (if not already installed):

   For macOS/Linux:

   brew install uv
   

2. Set Up Your Meraki MCP Project:

   cd mcp-splunk-meraki/MerakiMCP
   

3. Install dependencies using uv:

   uv init
   
   uv venv
   source .venv/bin/activate # or .venv\Scripts\activate on Windows
   
   uv add "mcp[cli]"
   uv add "meraki"  
   

4. Run the Meraki MCP Agent:

   python meraki_mcp.py
   

---