sheridan-lab-jack

sheridan-lab-jack

Provides AI agents with SSH-based tools to manage Nokia SR Linux network devices in ContainerLab environments. Enables retrieval of device information, interfaces, routes, and running configurations, plus the ability to configure network interfaces through natural language commands.

Category
Visit Server

README

sheridan-lab-jack — Network MCP Server

A Model Context Protocol (MCP) server that exposes 6 network management tools for a Nokia SR Linux device running in ContainerLab. Designed to be used with Claude Code as the AI agent.

Architecture

┌──────────────┐      MCP (stdio)      ┌──────────────────┐      SSH       ┌──────────────┐
│  Claude Code │ ◄──────────────────► │  sheridan-lab-jack │ ◄──────────► │  Nokia SR    │
│  (AI Agent)  │                      │  (MCP Server)      │              │  Linux       │
└──────────────┘                      └──────────────────┘              │  (ContainerLab)│
                                                                        └──────────────┘

Tools (6 total)

Read Tools (5)

Tool Description
get_device_info Returns hostname, software version, chassis type, uptime
get_interfaces Lists all interfaces with admin/oper state and IP addresses
get_routes Shows the full routing table
get_running_config Retrieves running configuration (full or by section)
get_network_instances Lists all VRFs/network-instances and their interfaces

Write Tools (1)

Tool Description
configure_interface Sets IP address, admin state, and description on an interface

Prerequisites

  • Linux (Ubuntu 20.04+ recommended)
  • Docker (20.10+)
  • ContainerLab (0.44+)
  • Python 3.10+
  • Claude Code CLI (requires Anthropic Pro subscription)
  • sshpass (sudo apt install sshpass)

Quick Start

1. Install ContainerLab

sudo bash -c "$(curl -sL https://get.containerlab.dev)"

2. Start the Lab

cd sheridan-lab-jack
sudo containerlab deploy --topo topology.yml

Wait ~60 seconds for SR Linux to fully boot. Verify with:

sudo docker ps  # should show clab-sheridan-lab-jack-srl running

3. Install Python Dependencies

pip install -r requirements.txt
sudo apt install sshpass -y

4. Test SSH Connectivity

sshpass -p 'NokiaSrl1!' ssh -o StrictHostKeyChecking=no admin@clab-sheridan-lab-jack-srl -- "info from state /system information"

5. Connect Claude Code

cd sheridan-lab-jack
claude

Claude Code automatically reads .mcp.json from the project directory. Once inside Claude Code, verify with:

> use get_device_info to check the device

Environment Variables

Variable Default Description
DEVICE_HOST clab-sheridan-lab-jack-srl Hostname or IP of the SR Linux container
DEVICE_USERNAME admin SSH username
DEVICE_PASSWORD NokiaSrl1! SSH password

Credentials are never hardcoded in the server code. They are read from environment variables at runtime and passed via .mcp.json.

Input Validation

All write tools validate inputs before execution:

  • IP addresses: Dotted-decimal regex validation
  • Prefix lengths: Range check (0-32)
  • Interface names: Pattern matching for SR Linux format (ethernet-X/Y, lo0, mgmt0, system0)
  • Hostnames: RFC-compliant alphanumeric + hyphens, 1-63 chars
  • Descriptions: Alphanumeric with basic punctuation, max 80 chars
  • Config section names: Alphanumeric and hyphens only

Cleanup

sudo containerlab destroy --topo topology.yml

Example Claude Code Session

You: get device info
Claude: [calls get_device_info] The device is a Nokia SR Linux running version...

You: show me all interfaces
Claude: [calls get_interfaces] Here are the interfaces...

You: configure ethernet-1/1 with IP 192.168.50.1/24 and description "uplink"
Claude: [calls configure_interface] Successfully configured ethernet-1/1...

You: verify the change by showing interfaces again
Claude: [calls get_interfaces] Confirmed — ethernet-1/1 now has IP 192.168.50.1/24...

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured