How to Get Started with Itential MCP in Microsoft Copilot AI Studio

Overview

[The Model Context Protocol (MCP) is rapidly becoming the universal standard for connecting AI assistants to real-world tools, APIs, and infrastructure. Thanks to its standardized JSON-RPC interface, MCP enables any AI agent to securely discover and use external capabilities without specialized integration logic. Itential’s MCP Server brings enterprise-grade network and infrastructure automation to MCP-aware AIs including Microsoft Copilot, Microsoft Copilot Studio/AI Studio, OpenAI, Anthropic, Google Gemini, and more. This guide walks you through end-to-end setup, including:

• Installing and running the Itential MCP Server
• Configuring authentication (OAuth, Basic Auth)
• Integrating MCP inside Microsoft Copilot AI Studio
• Creating a Copilot Agent with MCP
• Auto-discovering Itential tools and resources
• Testing your agent with real Itential platform interactions

By the end, you’ll have a functioning Copilot agent that can manage infrastructure with natural language – safely and with full visibility.

What is MCP?

MCP (Model Context Protocol) is an open standard introduced to standardize how AI assistants interact with external systems. It provides three foundational capabilities:

1. Tools

Executable functions exposed by an MCP server. Examples from Itential MCP:

• get_devices
• get_health
• launch_workflow
• query_inventory

2. Resources

Structured data access such as files, logs, or inventory payloads.

3. Prompts

Reusable workflow templates an AI can use as tasks.

Why MCP Matters

• Universal connectivity across AI ecosystems.
• Zero bespoke integrations required.
• Instant tool discovery.
• Enterprise-grade security through standardized auth and isolation.

How Itential Safely Brings AI to Enterprise Infrastructure

The Itential MCP Server provides the safe execution layer bridging AI and enterprise infrastructure. Itential handles execution, authentication, RBAC, and audit logging – while the AI provides reasoning and intent interpretation.

When a Copilot agent says: “Show me the devices in the Texas data center.”

Copilot → MCP → Itential Platform → Inventory results → Copilot formats for the user.

This separation of responsibilities keeps automation safe, repeatable, and governed.

Installation Options & Authentication Setup for Itential MCP

Full installation steps are available here →

This guide keeps installation high-level to focus on Copilot integration. Authentication options supported:

• OAuth
• Basic Auth

(See the repository for complete configuration details.)

Configuring MCP in Microsoft Copilot AI Studio

Microsoft added MCP support to Copilot AI Studio and Custom Copilot Agents starting in 2025. MCP servers can be added as external tool providers

Step 1: Open Copilot AI Studio

Navigate to: https://copilotstudio.microsoft.com/

Create your agent

1. Go to Build → Copilot Agents → New Agent

2. Give your agent a name (e.g., Infrastructure Assistant)

Step 2: Add a New MCP Connection

Creating an MCP-Enabled Copilot Agent

1. Go to tools section of agent.

2. Choose Custom Knowledge + MCP Tools.

3. In Tools, enable your MCP Server:

✔ itential-mcp

4. Choose Auto-discovery enabled (recommended)

Once saved, the Copilot agent will automatically pull from the Itential MCP server:

• tools
• resources
• schemas

This means your agent instantly becomes infrastructure-aware.

Discovering Tools in Copilot

Inside AI Studio, go to: Tools → MCP Tools → itential-mcp

You should now see a list such as:

• get_health
• get_devices
• get_workflows
• run_workflow
• launch_gm_service
• get_configuration
• etc.

Each tool shows:

• description
• input schema
• output schema

Copilot automatically understands how to call them.

Testing the Agent with Itential MCP Tools

Once your Copilot agent is published, open the Test Console and try these.

1. Platform Health

Prompt: “Using Itential MCP, check the Itential platform health.” Expected:

• platform availability
• API readiness
• subsystem health

2. Inventory Access

Prompt: “Show me all devices in the Atlanta data center.”

Returns:

• devices
• management IPs
• platform metadata

3. Workflow Inspection

Prompt: “List all automation workflows available in Itential.”

Useful for:

• configuration compliance
• provisioning
• network automation flows

4. Device Configuration

Prompt: “Get the running configuration for router R1.”

Returns:

• sanitized show output
• version
• compliance info

5. Launch Any Services with Dynamic Binding & Agent Persona

Prompt: “Launch AWS EC2 list service for us-west-1.”

6. Start a Workflow

Prompt: “Run the Port Turn Up workflow.”

Copilot will ask for missing parameters automatically.

What You Can Do with Your New Copilot Agent

You now have a fully integrated, MCP-powered Copilot agent that can:

• Discover Itential tools
• Interact with your infrastructure
• Run automation workflows
• Query inventory
• Retrieve configurations
• Make decisions with enterprise governance

This combination – MCP + Itential + Microsoft Copilot – creates a powerful and safe automation stack:

With this foundation in place, your organization can begin building advanced AI-driven operations at scale.

Now that you have your MCP-powered copilot ready, here’s a few things you can do next:

• Build custom prompts for common operational tasks
• Add additional Itential tools for specialized workflows
• Publish your Copilot agent to Teams or internal portals
• Share your MCP configuration with your automation team
• Explore: https://github.com/itential/itential-mcp