Unimus MCP Server
A read-only server for the Unimus network configuration management system.
Unimus MCP Server
"Talk" to your network configurations as you would a colleague.
Meet the Unimus MCP, symbolized by our LEGO parrot. Just as a parrot synthetically mimics human speech, this server allows you to "talk" to your Unimus network using natural language (LLMs). Ask a question about a backup, search for a specific configuration, or request the network topology; our parrot translates it into the correct, safe, read-only API calls.
This project is a read-only Model Context Protocol server for the Unimus network management platform. It exposes all your network data for conversational AI, making complex queries and analyses easier than ever.
📚 Documentation
📖 Complete Documentation - Visit Our Wiki
- Installation & Setup - Get started quickly
- Docker Deployment - Container deployment guide
- API Reference - All 15 MCP tools
- Usage Examples - Example queries and use cases
- Development & Roadmap - Contributing and roadmap
Quick Start
Docker (Recommended) 🐳
docker run -d \
--name unimus-mcp \
-e UNIMUS_URL="https://your-unimus.example.com" \
-e UNIMUS_TOKEN="your-api-token" \
-p 8080:8080 \
controlaltautomate/unimus-mcp:latest
Python Installation
git clone https://github.com/Deployment-Team/unimus-mcp.git
cd unimus-mcp
pip install .
Current Version
Version: 1.0.0 (Production-Ready Enterprise Network Intelligence)
🎉 FULLY TESTED & VALIDATED: All 15 MCP tools tested against live Unimus instance
Key Features
- 15 MCP Tools: Complete device and backup management
- Enhanced Metadata: 12 comprehensive calculated fields for device analysis
- Flexible Attributes: Granular control over device data retrieval
- Backup Content Search: Regex pattern matching in configurations
- Network Topology: Device relationship analysis and topology mapping
- Change Tracking: Find devices with recent configuration changes
- Docker Ready: Enterprise-grade containerization with health checks
- 100% Tested: Validated against live Unimus instances
Requirements
- Python 3.10+
- Unimus 1.7.x or newer (API v.2 support)
- Valid Unimus API token with read permissions
Configuration
Set these environment variables:
UNIMUS_URL: Full URL to your Unimus instanceUNIMUS_TOKEN: API token from Unimus
Example Usage
> Show me all Cisco devices in my network
> Get the latest backup for device ID 15
> Search for "interface GigabitEthernet" in device backups
> Find devices that had backup changes in the last 24 hours
> Compare backup 100 with backup 105 and show differences
License
MIT License - see LICENSE for details.
Support
- Documentation: Visit Our Wiki
- Issues: GitHub Issues
- Discussions: GitHub Discussions
関連サーバー
Scout Monitoring MCP
スポンサーPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
スポンサーAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
JS Development MCP Server
A server for JavaScript/TypeScript development with intelligent project tooling and testing capabilities.
Omega Memory
Persistent memory for AI coding agents with semantic search, contradiction detection, memory decay, and cross-session learning. 25 MCP tools, local-first, #1 on LongMemEval (95.4%).
Remote MCP Server (Authless)
An authentication-free remote MCP server deployable on Cloudflare Workers.
GhidraMCP
An embedded MCP server for Ghidra, exposing program data and reverse engineering functionalities.
MCP Playground
A demonstration MCP server implementation in Go featuring real-time bidirectional file communication.
McpDocServer
An MCP-based server for searching and retrieving development framework documentation, supporting crawling and local file loading.
godoc-mcp-server
MCP server to provide golang packages and their information from pkg.go.dev
xcsimctl
Manage Xcode simulators.
MCP-Haskell
A complete Model Context Protocol (MCP) implementation for Haskell, supporting both StdIO and HTTP transport.
Meta MCP Server
An MCP server for intelligent tool routing, using a Qdrant vector database and LM Studio for embeddings.