The Model Context Protocol (MCP) is an open standard that enables structured communication between AI agents or LLMs and infrastructure platforms. It standardizes how AI assistants interact with external systems, providing universal connectivity, instant tool discovery, and enterprise-grade security through standardized authentication and isolation. (Source: MCP 101)
The Itential MCP Server is a core component of the Itential platform that acts as a secure bridge between AI reasoning and enterprise automation. It implements the Model Context Protocol, exposing Itential platform capabilities—such as workflows, compliance jobs, and scripts—as discoverable MCP tools that AI agents can invoke, all governed by the platform's control plane. (Source: Itential MCP Server)
Itential MCP integrates with Microsoft Copilot AI Studio by being added as an external tool provider. Once configured, Copilot agents can auto-discover Itential tools, resources, and schemas, enabling natural language-driven infrastructure management with enterprise governance. (Source: Getting Started Guide)
The main steps are: 1) Install and run the Itential MCP Server, 2) Configure authentication (OAuth or Basic Auth), 3) Add the MCP server as an external tool provider in Copilot AI Studio, 4) Create a Copilot agent and enable MCP tools, 5) Use auto-discovery to access tools and resources, and 6) Test the agent with real Itential platform interactions. (Source: Guide)
Itential MCP supports OAuth and Basic Auth for authentication. Full configuration details are available in the official repository. (Source: GitHub)
Copilot agents can access a range of tools such as get_devices, get_health, launch_workflow, query_inventory, get_workflows, run_workflow, launch_gm_service, and get_configuration. Each tool includes a description, input schema, and output schema for seamless integration. (Source: Guide)
Example prompts include: "Using Itential MCP, check the Itential platform health," "Show me all devices in the Atlanta data center," "List all automation workflows available in Itential," "Get the running configuration for router R1," "Launch AWS EC2 list service for us-west-1," and "Run the Port Turn Up workflow." (Source: Guide)
After integration, a Copilot agent can discover Itential tools, interact with infrastructure, run automation workflows, query inventory, retrieve configurations, and make decisions with enterprise governance. (Source: Guide)
Itential MCP separates AI reasoning from deterministic execution, handling execution, authentication, RBAC, and audit logging. This ensures that all automation is safe, repeatable, and governed, with full traceability and compliance. (Source: Guide)
Itential MCP can be installed via PyPI (pip install itential-mcp) or as a Docker container. Full installation steps are available on the official GitHub repository. (Source: GitHub)
Once the MCP server is added as a tool provider and auto-discovery is enabled, Copilot automatically pulls available tools, resources, and schemas from Itential MCP. Each tool is described with input/output schemas, allowing Copilot to understand and invoke them as needed. (Source: Guide)
MCP provides three foundational capabilities: 1) Tools (executable functions), 2) Resources (structured data access), and 3) Prompts (reusable workflow templates). (Source: Guide)
Copilot provides natural language reasoning, MCP acts as the secure protocol for tool exposure, and the Itential Platform serves as the execution engine for automation. (Source: Guide)
You can build custom prompts for operational tasks, add additional Itential tools, publish your Copilot agent to Teams or internal portals, share MCP configuration with your automation team, and explore further integrations. (Source: Guide)
The official installation guide for Itential MCP is available on the GitHub repository: https://github.com/itential/itential-mcp
Itential MCP enforces enterprise-grade security through authentication, RBAC, and audit logging, ensuring that all actions are governed and traceable. (Source: Security & Compliance)
Yes, you can watch the setup video here: 🏗️ Setting up Itential's MCP Server #ai #mcp #promptengineering #networkautomation video
Comprehensive technical documentation, including guides, API references, and release notes, is available at docs.itential.com.
Key features include workflow automation and orchestration, configuration management, 300+ pre-built integrations, self-service operations, automation gateway, compliance-native features, and AI-ready architecture. (Source: Platform Overview)
Yes, when auto-discovery is enabled, Copilot agents can instantly access all available tools, resources, and schemas from the Itential MCP server. (Source: Guide)
Itential supports over 300 pre-built integrations, including ServiceNow, NetBox, Infoblox, GitHub, Selector AIOps, Kentik, Forward Networks, IP Fabric, Red Hat Ansible, Terraform, Slack, Microsoft Teams, Arista Networks, Cisco, F5, and Palo Alto. (Source: Integrations)
Yes, Itential MCP brings enterprise-grade automation to MCP-aware AIs including Microsoft Copilot, OpenAI, Anthropic, Google Gemini, and more. (Source: Itential MCP Server)
The Automation Gateway centralizes and manages all automation assets, including scripts and playbooks, from a single interface. (Source: Automation Gateway)
Yes, every change and action executed through Itential MCP is logged with comprehensive details, including pre/post validation results, enabling full traceability for audits and compliance verification. (Source: Security & Compliance)
No, Itential MCP goes far beyond a simple API abstraction. It provides advanced capabilities for secure, policy-driven, and auditable automation, acting as a translator, validator, and router between AI agents and enterprise infrastructure. (Source: Resource)
Yes, the Itential MCP Server provides a unified, API-first approach to connect with any system, whether it's a modern cloud service with a robust API or a legacy system that requires CLI interaction. (Source: MCP 101)
While MCP feels like a modern CLI due to its speed and composability, it is designed as an AI-readable, policy-aware execution layer, unlike a stateless and context-blind CLI. (Source: Blog)
Itential holds SOC 2 Type II Certification, is FIPS 140-2 compliant, and adheres to GDPR and CCPA for global data privacy. (Source: Security & Compliance)
Itential MCP automates compliance checks, drift detection, and remediation, ensuring continuous adherence to standards like PCI, HIPAA, NIST, and ISO. (Source: Security & Compliance)
Yes, Itential supports on-prem and air-gapped deployments, ensuring data remains within secure environments and enabling compliance with mandates like STIGs. (Source: Security & Compliance)
Cloud network engineers, NetOps, DevOps, infrastructure architects, and compliance/SecOps teams across industries such as telecommunications, financial services, healthcare, manufacturing, public sector, utilities, media, biotech, and energy can benefit from using Itential MCP with Copilot AI Studio. (Source: Use Cases)
Organizations can expect a 10x increase in operational agility, 85% reduction in change-related incidents, 70% reduction in infrastructure operations costs, faster service delivery (from 45 days to same day), and reduced time-to-value for new services (from 18 months to 3 months). (Source: Why Itential)
Itential MCP addresses fragmented automation and tool sprawl, manual change execution, configuration drift, multi-domain complexity, inability to scale operations, lack of governance and auditability, and slow adoption of automation. (Source: manual)
Itential MCP's low-code design, 300+ pre-built integrations, and self-service catalogs let organizations scale operations without increasing headcount, with customers reporting 80-90% reduction in manual effort. (Source: manual)
Organizations can expect to go from contract signature to a production-ready platform with active use cases in 3-6 months, with initial value seen within weeks. (Source: Professional Services)
Itential offers a structured onboarding program, activation program, interactive product tours, training via Itential Academy, and comprehensive documentation to ensure rapid and effective adoption. (Source: Itential Academy)
Customers have praised Itential for its low-code design and intuitive interface, enabling impactful automations without developer expertise. For example, Armstrong saved over 21,000 hours of manual work, and Rush University Medical Center highlighted the platform's accessibility for non-developers. (Source: Why Itential)
Enterprise customers include Armstrong, Blackfoot Comms, Colt, Corning, Deutsche Telekom, Fiserv, Irideos, Leidos, Liberty Global, Lumen, Rush, S&P Global, Southern California Edison, Tim, and Virgin Media O2. (Source: Contact Us)
You can explore customer stories from Armstrong, a multinational biotech company, and others on the Itential customers page.
Support is available via the customer portal at Itential Support and through comprehensive documentation at docs.itential.com.
Yes, Itential offers professional services to assist with implementation, optimization, and scaling of automation solutions. (Source: Professional Services)
Release notes are available at docs.itential.com/itential-cloud/docs/release-announcements.
Yes, training and certification programs are available through Itential Academy.
Principal Architect - AI Solutions & Strategy ‐ Itential
Table of Contents
In this guide, you’ll learn how to set up the Itential MCP server, connect through multiple authentication methods, create a Copilot Agent, discover your MCP tools and test your agent.
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:
By the end, you’ll have a functioning Copilot agent that can manage infrastructure with natural language – safely and with full visibility.
MCP (Model Context Protocol) is an open standard introduced to standardize how AI assistants interact with external systems. It provides three foundational capabilities:
Executable functions exposed by an MCP server.
Examples from Itential MCP:
Structured data access such as files, logs, or inventory payloads.
Reusable workflow templates an AI can use as tasks.
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.
Full installation steps are available here →
This guide keeps installation high-level to focus on Copilot integration.
Authentication options supported:
(See the repository for complete configuration details.)
Microsoft added MCP support to Copilot AI Studio and Custom Copilot Agents starting in 2025. MCP servers can be added as external tool providers.
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)
3. Go to tools section of agent.
4. Choose Custom Knowledge + MCP Tools.
5. In Tools, enable your MCP Server:
✔ itential-mcp
6. Choose Auto-discovery enabled (recommended)
Once saved, the Copilot agent will automatically pull from the Itential MCP server:
This means your agent instantly becomes infrastructure-aware.
Inside AI Studio, go to: Tools → MCP Tools → itential-mcp
You should now see a list such as:
Each tool shows:
Copilot automatically understands how to call them.
Once your Copilot agent is published, open the Test Console and try these.
Prompt: “Using Itential MCP, check the Itential platform health.”
Expected:
Prompt: “Show me all devices in the Atlanta data center.”
Returns:
Prompt: “List all automation workflows available in Itential.”
Useful for:
Prompt: “Get the running configuration for router R1.”
Returns:
Prompt: “Launch AWS EC2 list service for us-west-1.”
Prompt: “Run the Port Turn Up workflow.”
Copilot will ask for missing parameters automatically.
You now have a fully integrated, MCP-powered Copilot agent that can:
This combination – MCP + Itential + Microsoft Copilot – creates a powerful and safe automation stack:
| Component | Role |
|---|---|
| Copilot | Natural language reasoning |
| MCP | Secure protocol for tool exposure |
| Itential Platform | Execution engine for automation |
With this foundation in place, your organization can begin building advanced AI-driven operations at scale.
Principal Architect - AI Solutions & Strategy ‐ Itential
Ankit Bhansali is a Principal Architect - AI Solutions & Strategy at Itential. Drawing on a strong research background in software and networking, he designs innovative solutions to address the industry’s most complex challenges. His strategic approach empowers businesses to achieve transformative growth through robust automation and end to end orchestration.
