MCP Public Cloud (Infra)
Unizo's Public Cloud (Infra) Management MCP Server provides a unified, agent-friendly interface for managing infrastructure resources and user access across different cloud platforms and organizational structures. Integrated via the Model Context Protocol (MCP), this server enables AI agents and LLM clients to interact with infrastructure provisioning, user management, resource monitoring, and compute orchestration workflows.
Designed for modern DevOps and cloud automation, this guide outlines installation, tool reference, and runtime configuration required to use the Unizo Public Cloud (Infra) Management MCP Server.
Overview
The Unizo Public Cloud (Infra) Management MCP Server enables seamless integration of cloud infrastructure systems with AI agents through a standardized interface that abstracts the complexity of different cloud platforms.
Key Benefits
- Unified Infrastructure Orchestration: Streamline resource management across cloud providers and environments with a single API interface that normalizes operations from different platforms
- AI Agent Compatibility: Built to integrate seamlessly with Claude, GPT, and other agents that speak the MCP protocol for automated infrastructure provisioning and management
- User-Centric Resource Management: Navigate complex organizational hierarchies with user-based resource allocation, access control, and audit trails
- Real-time Monitoring: Track resource states, performance metrics, and costs with comprehensive monitoring across compute, storage, and networking resources
Available Tools
Tool Reference
Tool Name | Description | Parameters |
---|---|---|
list_users | Retrieves all users in the infrastructure management system with pagination support | Required: integration_id, correlation_id Optional: offset, limit, sort |
list_user_resources | Lists all infrastructure resources allocated to a specific user with hierarchical filtering | Required: integration_id, user_id, correlation_id Optional: offset, limit, sort, parent_resource_id |
Installation & Setup
Prerequisites
- Node.js or Python runtime (based on your MCP proxy toolchain)
- MCP-compatible AI agent (e.g., Claude, GPT)
- Unizo Infrastructure Management API credentials (see environment setup below)
- Valid integration IDs for your connected cloud platforms
Example MCP Server Setup (JSON)
{
"mcpServers": {
"unizo": {
"command": "mcp-proxy",
"args": ["http://172.184.130.51:8999/mcp"],
"env": {
"API_ACCESS_TOKEN": "your_account_token"
}
}
}
}
Integrate this Infrastructure Management server alongside your Unizo Incident Management or EDR/XDR servers for complete infrastructure-to-response automation and end-to-end operational orchestration.
Environment Variables
Variable | Description |
---|---|
API_ACCESS_TOKEN | Your Unizo-issued API key for secure MCP authentication |
Client Integration Flow
-
Start the MCP Server
- Use your orchestrator (Claude Desktop, GPT plugin, or equivalent)
- Load the MCP JSON config with the unizo-infrastructure-management target
-
Discover User Base
- Call
list_users
to identify all infrastructure users - Use
get_user
for detailed user information and audit trails
- Call
-
Explore Resource Hierarchy
- Discover user resources with
list_user_resources
- Navigate resource hierarchies using
parent_resource_id
filtering - Get detailed resource information via
get_user_resource
- Discover user resources with
-
Monitor Resource States
- Track resource states (RUNNING, STOPPED, TERMINATED, PENDING, ERROR)
- Monitor compute details including CPU, memory, storage, and runtime configurations
- Review resource change logs and audit trails
The MCP server provides a consistent interface across different cloud platforms, allowing agents to use standardized tools regardless of the underlying infrastructure provider (AWS, Azure, GCP, etc.).
Observability & Logging
All infrastructure management tool invocations are comprehensively logged by the MCP server with full agent context, timestamped correlation IDs, and user attribution.
Early Access Program
The Unizo Infrastructure Management MCP Server is currently available through our Early Access Program. All customers can gain priority access to these powerful infrastructure management tools and receive dedicated implementation support.
Reach out to our team to schedule a personalized demo and discuss integration options for your organization. Connect With Us