API-Central

API-Central

Enables conversational automation of HPE Aruba Central network operations through Claude Code. Provides 88 tools across monitoring, configuration, and operations domains for device migration, SSID management, switch provisioning, and GreenLake Platform integration.

Category
访问服务器

README

API-Central — Aruba New Central Automation

Python tooling for HPE Aruba Central (New Central) — network device migration, SSID configuration, switch provisioning, and GreenLake Platform management.

Designed to work as a Claude Code MCP server so you can drive network operations conversationally, and as standalone CLI tools for batch migration workflows.


Features

  • 88 MCP tools across three domain servers (monitoring, config, ops)
  • 8-stage migration pipeline — discover devices → verify config → push to New Central
  • SSID build/delete with scope-map targeting (org-wide, site, or group)
  • Switch provisioning: VLANs, port profiles, SVIs
  • GreenLake Platform (GLP) subscription and device management
  • Async troubleshooting: ping, traceroute, cable test, PoE bounce, reboot

Prerequisites

  • Python ≥ 3.10
  • uv (recommended) or pip
  • HPE Aruba Central account with API credentials (OAuth2 client ID + secret)

Setup

# 1. Clone and install dependencies
git clone https://github.com/your-org/API-Central.git
cd API-Central
uv sync

# 2. Configure credentials
cp config/credentials.yaml.example config/credentials.yaml
# Edit config/credentials.yaml — fill in client_id, client_secret, base_url

# 3. Configure MCP servers (for Claude Code integration)
cp .mcp.json.example .mcp.json
# Edit .mcp.json — replace /path/to/API-Central with your actual clone path

Security: config/credentials.yaml and .mcp.json are git-ignored. Never commit them.


Usage

Claude Code MCP integration

Once .mcp.json is configured, start Claude Code from this directory — the three MCP servers (aruba-monitoring, aruba-config, aruba-ops) will load automatically.

Example prompts:

  • "List all devices at the Home Lab site"
  • "Build a WPA3 SSID called Corp-WiFi on VLAN 100 for all APs"
  • "Ping 8.8.8.8 from switch SN123456"

CLI — Migration pipeline

python run_pipeline.py --input inputs/devices.csv

Runs the full 8-stage migration (discover → assign → configure → verify). Idempotent — safe to re-run.

CLI — SSID builder

python run_ssid.py

Interactive SSID build/delete workflow.


Project layout

mcp_servers/
  monitoring.py       Monitoring tools (health, trends, wireless metrics)
  config.py           Config tools (SSIDs, VLANs, profiles, webhooks, firmware)
  ops.py              Ops tools (reboots, ping, cable test, PoE bounce, GLP)
  shared.py           Shared utilities
pipeline/
  clients/            CentralClient, GLPClient, MCPClient, TokenManager
  stages/             s1_discover → s8_verify
  config.py           Credential loader
  ssid_underlay.py    SSID build/delete logic
config/
  credentials.yaml.example   Template — copy to credentials.yaml and fill in
resources/            Postman download script (collections git-ignored — see resources/README.md)
inputs/               CSV templates for batch migration
tests/                Unit + integration tests

Running tests

pytest tests/

All tests use mock credentials — no real API calls.


Documentation

See CLAUDE.md for:

  • Full MCP tool reference and verb/noun naming conventions
  • Scope and device-type translation rules
  • API endpoint patterns
  • Token cost optimization tips

Security

  • Credentials load at runtime from config/credentials.yaml (git-ignored)
  • No secrets are hardcoded in source files
  • Token cache files (.token_cache_*.json) are git-ignored
  • MCP server config (.mcp.json) is git-ignored — it contains local paths

Report security issues via GitHub Issues — do not include credentials in bug reports.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选