Meraki MCP Server
Enables interaction with the Meraki Dashboard API for LLMs, allowing seamless integration of Meraki network management capabilities within an AI assistant's conversational interface.
README
Meraki MCP Server DONOTTRUST
I no longer work for Cisco so will not be updating this repo.
This Model Context Protocol (MCP) server enables interaction with the Meraki Dashboard API for LLMs, allowing for seamless integration of Meraki network management capabilities within an AI assistant's conversational interface.
Warning
Do not use if your organization prohibits you or you do not feel comfortable sending data to an AI assistant. This tool will send sensitive information such as serial numbers, hostnames, MAC addresses, and other information obtained through Meraki Dashboard APIs.
Environment
- node v23.7.0
- npm v10.9.2
- Meraki Dashboard API key
- Claude Desktop App
Building the MCP
- Clone this repository:
git clone git@github.com:yujiterada/mcp-server-meraki-donottrust.git
cd mcp-server-meraki-donottrust
- Install dependencies:
npm install
- Set up environment variables:
cp .env.sample .env
-
Edit the
.envfile:- Set your
MERAKI_DASHBOARD_API_KEYfrom your Meraki Dashboard - Configure API endpoint scopes by setting the following variables to
trueorfalse:ADMINISTERED_API_ENABLEDAPPLIANCE_API_ENABLEDCAMERA_API_ENABLEDCAMPUS_GATEWAY_API_ENABLEDCELLULAR_GATEWAY_API_ENABLEDDEVICES_API_ENABLEDINSIGHT_API_ENABLEDLICENSING_API_ENABLEDNETWORKS_API_ENABLEDORGANIZATIONS_API_ENABLEDSECURE_CONNECT_API_ENABLEDSENSOR_API_ENABLEDSM_API_ENABLEDSWITCH_API_ENABLEDWIRELESS_API_ENABLEDWIRELESS_CONTROLLER_API_ENABLED
Note: It's recommended to enable only the API endpoint scopes you need, as enabling all scopes might exceed Claude's context limits. Chat length is vrey limited on free version of Claude and therefore, the user will need to enable/disable spefici API endpoints from Claude app.
- Set your
-
Build the project:
npm run build
Adding MCP to Claude Desktop App
-
Open Claude Desktop App
-
Go to Settings
-
Navigate to the MCP section
-
Click "Developer" on the left hand side
-
Click "Edit Config"
-
Create/Edit a file entering the following details:
macOS
{ "mcpServers": { "meraki": { "command": "node", "args": [ "--env-file=/path/to/mcp-server-meraki/.env", "/path/to/mcp-server-meraki/build/index.js" ] } } }Windows
{ "mcpServers": { "meraki": { "command": "C:\\path\\to\\node.exe", "args": [ "--env-file=C:\\path\\to\\mcp-server-meraki-donottrust\\.env", "C:\\path\\to\\mcp-server-meraki-donottrust\\build\\index.js" ] } } } -
Restart app
Future Development
The following improvements are planned for future development:
-
TypeScript Integration
- Add TypeScript interfaces for all API responses
- Implement Zod schemas for runtime type validation
- Improve type safety across the codebase
-
Dynamic API Scope
- Explore implementing Meraki Dashboard API scopes as Tools
- Allow users to select which APIs to use directly from Claude's interface
- Eliminate the need for .env file modifications and rebuilds
-
Security Enhancements
- Implement encryption for sensitive information
- Add secure decoding mechanisms within the MCP
- Enhance API key management and security
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
MIT License
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。