Skip to main content
Glama
MCP Nautobot Server

MCP Nautobot Server

by aiopnet

MCP-Nautobot

MCP Python 3.10+ License: MIT Code style: black

A Model Context Protocol (MCP) server for Nautobot network automation platform. This project allows AI assistants to interact with your Nautobot instance, providing access to network inventory data.

Disclaimer: This project is not officially affiliated with Anthropic, Claude, or Nautobot. It is an independent implementation of the Model Context Protocol for Nautobot integration.

Features

  • Asynchronous API: Built with modern async Python

  • MCP Compatible: Works with Claude and other MCP-compatible AI assistants

  • Nautobot Integration: Query your network inventory data directly

  • Site Information: Retrieve detailed site location data

  • Device Details: Access device specifications and configurations

  • Network Topology: Visualize network connections and relationships

  • Role-based Access: Control data access by user role

  • Flexible Configuration: Customizable data presentation

Related MCP server: Notion MCP Server

Requirements

  • Python 3.10+

  • Nautobot instance with API access

  • Nautobot API token with appropriate permissions

Installation

# Clone the repository
git clone https://github.com/aiopnet/mcp-nautobot.git
cd mcp-nautobot

# Create and activate a virtual environment
# If uv is not installed, follow instructions at: https://github.com/astral-sh/uv
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Install dependencies
uv pip install -e .  # Requires pip 21.3+ for editable installs with pyproject.toml

Configuration

Copy the example environment file and update it with your settings:

cp .env.example .env
# Edit .env with your favorite editor

Environment Variables

Variable

Required

Description

Default

NAUTOBOT_URL

Yes

URL of your Nautobot instance

None

NAUTOBOT_TOKEN

Yes

API token with read permissions

None

MCP_PORT

No

Port for the MCP server to listen on

8000

MCP_HOST

No

Host for the MCP server to bind to

127.0.0.1

LOG_LEVEL

No

Logging level (DEBUG, INFO, WARNING, ERROR)

INFO

⚠️ Security Note: Never commit your .env file to version control. It contains sensitive API tokens.

For advanced configuration options, see docs/CONFIGURATION.md.

Usage

Running the Server

# Start the MCP server
python -m mcp_nautobot.server

# Or using the provided CLI
mcp-nautobot-server

The server will start on http://127.0.0.1:8000 by default.

Integrating with Claude Desktop

  1. Open Claude Desktop and navigate to Settings > Tools > Configure Custom Tools

  2. Add a new tool with the following details:

    • Name: Nautobot Network Data

    • Description: Access network inventory data from Nautobot

    • Schema Type: MCP

    • Endpoint URL: http://127.0.0.1:8000 (or your custom host/port)

  3. Save and test the connection

Now you can ask Claude questions about your network inventory:

  • "What sites do we have in the US West region?"

  • "Show me all devices in the Chicago datacenter"

  • "List all Cisco switches in our network"

  • "What's the IP address of the core router in Atlanta?"

Developer Guide

Testing

# Install development dependencies
uv pip install -e ".[dev]"

# Run tests
pytest

# Run tests with coverage
pytest --cov=mcp_nautobot

Code Style and Linting

This project follows PEP 8 guidelines and uses Black and isort for formatting.

# Format code
black mcp_nautobot tests
isort mcp_nautobot tests

# Lint code
flake8 mcp_nautobot tests
mypy mcp_nautobot

Roadmap

  • Device Configuration Retrieval: Access running device configurations

  • Topology Visualization: Generate network maps and diagrams

  • Multi-tenant Support: Enhanced role-based access control

  • Circuit Information: Data about WAN circuits and providers

  • Performance Data: Historical performance metrics integration

Contributing

Contributions are welcome! Please check out our Contributing Guide to get started.

If you encounter any issues or have feature requests, please open an issue.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgements


## Troubleshooting

If you encounter issues, check the [Troubleshooting Guide](docs/TROUBLESHOOTING.md) or open an issue on GitHub.

Available Tools

5 tools
get_ip_address_by_idB

Retrieve a specific IP address by its Nautobot ID

Inputs: ip_id (required).

get_ip_addressesC

Retrieve IP addresses from Nautobot with filtering options

Inputs: address, prefix, status, role, +4 more.

get_prefixesC

Retrieve network prefixes from Nautobot with filtering options

Inputs: prefix, status, site, role, +4 more.

search_ip_addressesB

Search IP addresses using a general query string

Inputs: query (required), limit.

test_connectionB

Test the connection to the Nautobot API

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 5 tools

    Disambiguation4/5

    Most tools have distinct purposes: get_ip_address_by_id retrieves a specific IP, get_ip_addresses lists IPs with filters, get_prefixes handles prefixes, and test_connection is unique. However, get_ip_addresses and search_ip_addresses have some overlap, as both involve retrieving IP addresses, which could cause mild confusion about when to use each.

    Naming Consistency5/5

    All tool names follow a consistent snake_case pattern with clear verb_noun structures (e.g., get_ip_address_by_id, search_ip_addresses). The naming is predictable and readable across all five tools, with no deviations in style.

    Tool Count4/5

    With 5 tools, the count is reasonable for a server focused on IP address and prefix management in Nautobot. It's slightly lean but covers core retrieval and testing operations without feeling bloated, though it could benefit from more actions like create or update tools.

    Completeness2/5

    The tool set is severely incomplete for managing IP addresses and prefixes in Nautobot. It only provides retrieval and search operations, with no tools for creating, updating, or deleting IP addresses or prefixes. This leaves significant gaps that will hinder agents from performing full lifecycle management.

    Related MCP Connectors

    Related MCP Servers