Cisco Modeling Labs
An MCP server that provides access to common Cisco Modeling Labs (CML) operations.
What is Cisco Modeling Labs?
Cisco Modeling Labs is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server that provides access to common cisco modeling labs (cml) operations.
An MCP server that provides access to common Cisco Modeling Labs (CML) operations.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- An MCP server that provides access to common Cisco Modeling
Use Cases
Maintainer
Works with
Installation
NPM
npx -y cml-mcpPIP
pip install cml-mcpManual Installation
npx -y cml-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Cisco Modeling Labs
The Cisco Modeling Labs MCP server (cml-mcp) exposes over 50 tools for managing CML network simulation environments through natural language, covering lab lifecycle management, node configuration, link conditioning, packet capture, and user administration. Engineers can create complete virtual network topologies, start OSPF experiments, run CLI commands on simulated devices, and retrieve console logs — all without leaving their AI assistant. It supports PyATS integration for advanced device-level interactions.
Prerequisites
- Python 3.12, 3.13, or 3.14
- uv package manager (install from astral.sh/uv) — recommended for running via uvx
- Access to a Cisco Modeling Labs server version 2.9 or later
- CML credentials: URL, username, and password
- An MCP-compatible client such as Claude Desktop
Install uv package manager
The recommended installation uses uvx (bundled with uv) which downloads and runs cml-mcp without a permanent install.
# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"Gather your CML connection details
You need the URL of your CML server (e.g. https://cml.example.com), your login username, and password. If using a self-signed certificate, note that you will set CML_VERIFY_SSL=false.
Configure Claude Desktop with the CML MCP server
Add the cml-mcp server to your claude_desktop_config.json. The server is run via uvx with your CML credentials supplied as environment variables.
{
"mcpServers": {
"Cisco Modeling Labs (MCP)": {
"type": "stdio",
"command": "uvx",
"args": ["cml-mcp[pyats]"],
"env": {
"CML_URL": "https://cml.example.com",
"CML_USERNAME": "your_username",
"CML_PASSWORD": "your_password",
"CML_VERIFY_SSL": "true"
}
}
}
}Restart Claude Desktop
After saving the config file, restart Claude Desktop. The CML tools will appear in the tools list when the connection to your CML server is successful.
Optional: configure PyATS credentials for device CLI access
To run CLI commands directly on simulated devices via PyATS, add the PyATS credential environment variables to your config.
"env": {
"CML_URL": "https://cml.example.com",
"CML_USERNAME": "admin",
"CML_PASSWORD": "password",
"PYATS_USERNAME": "cisco",
"PYATS_PASSWORD": "cisco",
"PYATS_AUTH_PASS": "cisco"
}Cisco Modeling Labs Examples
Client configuration
Full Claude Desktop configuration for cml-mcp with PyATS support and SSL verification disabled for lab environments with self-signed certificates.
{
"mcpServers": {
"Cisco Modeling Labs (MCP)": {
"type": "stdio",
"command": "uvx",
"args": ["cml-mcp[pyats]"],
"env": {
"CML_URL": "https://cml.example.com",
"CML_USERNAME": "admin",
"CML_PASSWORD": "your_password",
"CML_VERIFY_SSL": "false",
"PYATS_USERNAME": "cisco",
"PYATS_PASSWORD": "cisco",
"PYATS_AUTH_PASS": "cisco"
}
}
}
}Prompts to try
Natural language prompts for managing Cisco Modeling Labs via the MCP server.
- "Create a new lab called 'OSPF Test Lab' with two CSR1000v routers connected together"
- "Start a packet capture on the link between Router1 and Router2"
- "Show me OSPF neighbors on Router1 and check adjacency status"
- "Apply 100ms latency and 1% packet loss conditioning to the WAN link"
- "List all running labs and their current status"
- "Delete the lab named 'Old BGP Test' and free its resources"Troubleshooting Cisco Modeling Labs
SSL certificate verification error when connecting to CML server
Set CML_VERIFY_SSL=false in your environment config if your CML server uses a self-signed certificate. For production deployments, install the CA certificate in your system trust store instead.
PyATS CLI commands fail or return connection errors
Ensure the PYATS_USERNAME, PYATS_PASSWORD, and PYATS_AUTH_PASS env vars match the credentials configured on your simulated devices. Also verify the lab is started and nodes are in the 'BOOTED' state before running CLI commands.
uvx cannot find cml-mcp or fails to download
Ensure uv is installed and on your PATH. Run 'uvx cml-mcp --version' manually to test. If on a restricted network, configure uv to use a private PyPI mirror by setting UV_INDEX_URL.
Frequently Asked Questions about Cisco Modeling Labs
What is Cisco Modeling Labs?
Cisco Modeling Labs is a Model Context Protocol (MCP) server that mcp server that provides access to common cisco modeling labs (cml) operations. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Cisco Modeling Labs?
Install via npm with the command: npx -y cml-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Cisco Modeling Labs?
Cisco Modeling Labs works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Cisco Modeling Labs free to use?
Yes, Cisco Modeling Labs is open source and available under the BSD-2-Clause license. You can use it freely in both personal and commercial projects.
Cisco Modeling Labs Alternatives — Similar Cloud Services Servers
Looking for alternatives to Cisco Modeling Labs? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Cisco Modeling Labs in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Cisco Modeling Labs?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.