The MCP server enables interaction with Cisco Modeling Labs (CML) using natural language, allowing users to manage network labs through AI applications. It facilitates tasks such as creating labs, configuring nodes, and retrieving status information without manual scripting.
From the registry: An MCP server that provides access to common Cisco Modeling Labs (CML) operations.

Please install the `cml-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Python 3.12 or 3.13** — Python runtime required for cml-mcp.
- **uv package manager** — Install uv (provides uvx). (https://docs.astral.sh/uv/)
- **Cisco Modeling Labs (CML) 2.9 or later** — Reachable CML server with credentials. (https://www.cisco.com/c/en/us/products/cloud-systems-management/modeling-labs/index.html)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["cml-mcp"]
- required environment variables:
- `CML_URL`: Your CML server URL. (example: `https://cml.example.com`)
- `CML_USERNAME`: CML login username. (example: `<username>`)
- `CML_PASSWORD`: CML login password. (example: `<password>`)
- optional environment variables:
- `CML_VERIFY_SSL`: Set to 'false' for self-signed certificates. (example: `false`)
- `PYATS_USERNAME`: PyATS device login username (only if using cml-mcp[pyats] for CLI command execution). (example: `<username>`)
- `PYATS_PASSWORD`: PyATS device login password. (example: `<password>`)
- `PYATS_AUTH_PASS`: PyATS enable/auth password. (example: `<password>`)
Note: For CLI command execution on devices, use `cml-mcp[pyats]` in args instead of `cml-mcp`. HTTP transport mode is also available — see INSTALLATION.md.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.CML_URLrequiredYour CML server address.CML_USERNAMErequiredYour CML login username.CML_PASSWORDrequiredYour CML login password.CML_VERIFY_SSLSet to 'false' if using self-signed certificates.MCP server for progressive tool usage at any scale (see https://klavis.ai)