ansible-mcp-server
Enables AI assistants to manage infrastructure using Ansible and Terraform with 58 tools for playbooks, provisioning, security scanning, and more.
README
Ansible MCP Server
A Model Context Protocol (MCP) server that enables AI assistants to manage infrastructure using Ansible and Terraform.
Features
-
58 Infrastructure Management Tools
- Ansible playbook creation and execution
- Terraform infrastructure provisioning
- Hardware discovery and inventory
- Security scanning and auditing
- Service deployment from catalog
- Network device management
- Environment management (test/staging/production)
-
AI-Optimized Design
- Flexible playbook creation accepting YAML strings
- Comprehensive error handling
- Context persistence between sessions
- Dynamic tool loading for services
-
Cross-Platform Support
- Linux server deployment
- Windows client support via SSE proxy
- Remote server management
Quick Start
Prerequisites
- Node.js 16+
- Ansible 2.9+
- Terraform (optional)
Installation
# Clone the repository
git clone https://github.com/yourusername/ansible-mcp-server.git
cd ansible-mcp-server
# Install dependencies
npm install
# Copy and configure environment
cp .env.example .env
# Edit .env with your settings
# Run the server
npm start
For Claude Desktop
Add to your Claude Desktop configuration:
{
"mcpServers": {
"ansible": {
"command": "node",
"args": ["/path/to/ansible-mcp-server/src/index.js"],
"env": {
"PROXMOX_HOST": "your-proxmox-host",
"PROXMOX_USER": "root@pam",
"PROXMOX_PASSWORD": "your-password"
}
}
}
}
Windows Users
For Windows Claude Desktop, use the SSE proxy:
- Deploy the MCP server to a Linux host
- Run the SSE server on the Linux host
- Configure Claude Desktop to use the Windows client
See Windows Setup Guide for details.
Available Tools
Ansible Tools
create-playbook-flexible- Create playbooks with YAML strings or objectsansible-playbook- Run Ansible playbooksansible-task- Run ad-hoc Ansible tasksansible-role- Execute Ansible rolesvalidate-playbook- Validate playbook syntaxcreate-role-structure- Generate Ansible role directories
Infrastructure Tools
hardware-scan- Comprehensive hardware discoverystorage-analysis- Storage and SMART health analysisnetwork-interfaces- Network adapter discoverydiscover-proxmox- Discover Proxmox VMsgenerate-inventory- Create Ansible inventories
Security Tools
security-quick-scan- Quick security assessmentsecurity-scan-ports- Port scanningsecurity-check-passwords- Password policy auditsecurity-audit-accounts- User account auditsecurity-check-ssh- SSH configuration audit
Service Management
browse-services- Browse service catalogdeploy-service- Deploy services from cataloglist-environments- List deployment environmentsdeploy-to-environment- Deploy with environment protection
Documentation
Testing
Run the comprehensive feature test suite:
# Run tests in development environment
npm test
# Test specific environments
npm run test:dev # Development
npm run test:qa # QA
npm run test:staging # Staging
npm run test:prod # Production
# Verbose output for debugging
npm run test:verbose
Our feature tests validate complete VM lifecycle workflows including:
- VM creation from Proxmox templates
- Service installation (Jenkins, etc.)
- Service verification and management
- VM deletion and cleanup
- MCP context management
See Testing Guidelines for detailed information.
Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Built for use with Claude and other AI assistants
- Uses the Model Context Protocol
- Powered by Ansible and Terraform
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.