Cisco Catalyst Center MCP Server

Cisco Catalyst Center MCP Server

Enables network management through Cisco Catalyst Center, providing tools for monitoring device health, tracking client data, and managing network issues. It also supports compliance and lifecycle management by retrieving EoX summaries and detailed security advisory status.

Category
访问服务器

README

Cisco Catalyst Center MCP Server

A Model Context Protocol (MCP) server for Cisco Catalyst Center, providing network management capabilities through structured tools.

Features

This MCP server provides focused, high-value tools for Cisco Catalyst Center:

Network Monitoring

  • get_client_counts - Get counts of wired and wireless clients connected to the network
  • get_network_devices - Query network device inventory with flexible filtering
  • get_network_health - Get overall network health by device category
  • get_site_health - Get health information for sites (areas and buildings)
  • get_client_detail - Get detailed information about a specific client by MAC address

Issues & Assurance

  • get_issues - Retrieve network issues with filtering by priority, status, and more

Compliance & Lifecycle Management

  • get_compliance_detail - Get detailed compliance status for devices (EOX, IMAGE, PSIRT, etc.)
  • get_compliance_count - Get aggregate count of devices by compliance criteria
  • get_eox_summary - Get network-wide End-of-Life/End-of-Support summary
  • get_eox_devices - Get EoX status for all devices in the network
  • get_eox_device_details - Get detailed EoX bulletins for a specific device

Prerequisites

  • Python 3.10 or higher
  • Cisco Catalyst Center instance (v2.3.7.9 or compatible)
  • Valid Catalyst Center credentials with API access

Installation

Using uv (Recommended)

  1. Install uv if you haven't already:
curl -LsSf https://astral.sh/uv/install.sh | sh
  1. Clone this repository or download the source code

  2. Initialize and install dependencies:

cd catalyst-center-mcp
uv sync
  1. Create a .env file from the example:
cp .env.example .env
  1. Edit .env with your Catalyst Center credentials:
CATALYST_CENTER_URL=https://your-catalyst-center.example.com
CATALYST_CENTER_USERNAME=your_username
CATALYST_CENTER_PASSWORD=your_password
CATALYST_CENTER_VERIFY_SSL=true

Usage

Running the MCP Server

Start the server in development mode:

uv run mcp dev src/server.py

Or run directly:

uv run src/server.py

The server will start and be available for MCP clients to connect to via stdio transport.

Using with Claude Desktop

Add this server to your Claude Desktop configuration file:

Option 1: Using environment variables directly

{
  "mcpServers": {
    "catalyst-center": {
      "command": "uv",
      "args": ["run", "src/server.py"],
      "cwd": "/path/to/catalyst-center-mcp",
      "env": {
        "CATALYST_CENTER_URL": "https://your-catalyst-center.example.com",
        "CATALYST_CENTER_USERNAME": "your_username",
        "CATALYST_CENTER_PASSWORD": "your_password",
        "CATALYST_CENTER_VERIFY_SSL": "true"
      }
    }
  }
}

Option 2: Using .env file (recommended)

Create a .env file in the project directory with your credentials, then:

{
  "mcpServers": {
    "catalyst-center": {
      "command": "uv",
      "args": ["run", "src/server.py"],
      "cwd": "/path/to/catalyst-center-mcp"
    }
  }
}

Tool Examples

Get Client Counts

# Get current wired and wireless client counts
result = await get_client_counts()
# Returns: {"wired_count": 150, "wireless_count": 75, "total_count": 225, "timestamp": "current"}

Get Network Devices

# Get all devices
devices = await get_network_devices()

# Filter by hostname
devices = await get_network_devices(hostname="switch.*")

# Filter by device family
devices = await get_network_devices(device_family="Switches and Hubs", limit=50)

Get Network Health

# Get current network health by device category
health = await get_network_health()
# Returns health scores for Access, Distribution, Core, Router, and Wireless devices

Get Issues

# Get all active P1 issues
issues = await get_issues(priority="P1", issue_status="ACTIVE")

# Get issues for a specific site
issues = await get_issues(site_id="site-uuid-here")

# Get AI-driven issues
issues = await get_issues(ai_driven="YES")

Get Site Health

# Get health for all sites
sites = await get_site_health()

# Get only building sites
sites = await get_site_health(site_type="BUILDING")

Get Client Detail

# Get detailed info for a specific client
client = await get_client_detail(mac_address="00:11:22:33:44:55")

Get Compliance Detail

# Get all non-compliant devices
compliance = await get_compliance_detail(compliance_status="NON_COMPLIANT")

# Get EOX compliance status for specific devices
compliance = await get_compliance_detail(
    compliance_type="EOX",
    device_uuid="device-uuid-1,device-uuid-2"
)

# Get PSIRT (security advisory) compliance
compliance = await get_compliance_detail(compliance_type="PSIRT", limit=100)

Get Compliance Count

# Count all non-compliant devices
count = await get_compliance_count(compliance_status="NON_COMPLIANT")

# Count devices with image compliance issues
count = await get_compliance_count(
    compliance_type="IMAGE",
    compliance_status="NON_COMPLIANT"
)

Get EoX Summary

# Get network-wide EoX summary
summary = await get_eox_summary()
# Returns: {"hardware_count": 15, "software_count": 8, "module_count": 3, "total_count": 26}

Get EoX Devices

# Get all devices with EoX alerts
devices = await get_eox_devices()

# Get with pagination for large networks
devices = await get_eox_devices(limit=50, offset=1)

Get EoX Device Details

# Get detailed EoX bulletins for a specific device
details = await get_eox_device_details(device_id="device-uuid-here")
# Returns detailed bulletin info with end-of-sale/support dates and URLs

Project Structure

catalyst-center-mcp/
├── src/
│   ├── __init__.py
│   ├── server.py       # FastMCP server with tool definitions
│   ├── client.py       # HTTP client for Catalyst Center API
│   ├── auth.py         # Authentication handler
│   └── config.py       # Configuration management
├── requirements.txt    # Python dependencies
├── .env.example       # Environment variable template
├── .gitignore         # Git ignore rules
└── README.md          # This file

Authentication

The server uses Catalyst Center's authentication API:

  1. Credentials are sent via Basic Auth to /dna/system/api/v1/auth/token
  2. A token is returned, valid for 1 hour
  3. The token is cached and used in the X-Auth-Token header for all API calls
  4. On 401 responses, the token is automatically refreshed

Error Handling

  • Configuration errors: The server validates required environment variables on startup
  • Authentication failures: Returns clear error messages for invalid credentials
  • Network errors: HTTP errors are propagated with meaningful messages
  • Token expiration: Automatically re-authenticates on 401 responses

Development

Adding New Tools

To add a new tool:

  1. Define a new function in src/server.py decorated with @mcp.tool()
  2. Add proper type hints and docstring
  3. Use the client instance to make API calls
  4. Return structured data as a dictionary

Example:

@mcp.tool()
async def get_something(param: str) -> dict[str, Any]:
    """
    Description of what this tool does.

    Args:
        param: Description of parameter

    Returns:
        Description of return value
    """
    response = await client.get("/dna/intent/api/v1/endpoint", params={"param": param})
    return response

License

This project is provided as-is for use with Cisco Catalyst Center.

API Reference

This server uses Cisco Catalyst Center Intent API v2.3.7.9. For full API documentation, refer to the Catalyst Center API documentation.

Troubleshooting

SSL Certificate Errors

If you encounter SSL certificate errors, you can disable SSL verification (not recommended for production):

CATALYST_CENTER_VERIFY_SSL=false

Connection Timeouts

The default timeout is 30 seconds. For slower networks, you may need to adjust the timeout in src/client.py.

Authentication Issues

  • Verify your credentials are correct
  • Ensure the user has API access permissions in Catalyst Center
  • Check that the Catalyst Center URL is accessible from your machine

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