🔌 Itential - MCP Server

What is 🔌 Itential - MCP Server?

An MCP server that connects LLMs to the Itential Platform, enabling AI assistants to manage network automations, orchestrate workflows, monitor platform health, and perform advanced network operations. It is designed for platform engineers and developers.

How to use 🔌 Itential - MCP Server?

Install via pip install itential-mcp, set platform credentials as environment variables (ITENTIAL_MCP_PLATFORM_HOST, ITENTIAL_MCP_PLATFORM_USER, ITENTIAL_MCP_PLATFORM_PASSWORD), and start the server with itential-mcp run. Optionally configure transport (stdio, SSE, HTTP), tool tags, and authentication via CLI flags or a configuration file. Docker images are also available.

Key features of 🔌 Itential - MCP Server

• 56+ automation tools across 10 tag categories
• Flexible transport: stdio, SSE, HTTP with optional TLS
• Dynamic tool discovery without code modifications
• Supports basic auth, OAuth 2.0, JWT, and RBAC
• Role-based tool configurations for different user types
• Filter tools using --include-tags and --exclude-tags

Use cases of 🔌 Itential - MCP Server

• Apply device configurations and run commands across network devices
• Execute and monitor workflows via AI-powered assistants
• Monitor real-time platform health and manage component lifecycles
• Build and manage resource models with CRUD operations
• Integrate with external systems through OpenAPI and Gateway Manager

FAQ from 🔌 Itential - MCP Server

What are the runtime requirements?

Python 3.10 or higher and access to an Itential Platform instance are required.

How do I authenticate to the Itential Platform?

Authentication can be done via basic auth (username/password) or OAuth 2.0 (client ID/client secret), configured through environment variables, CLI parameters, or a configuration file.

Which transport methods are supported?

The server supports stdio (default), SSE, and HTTP transports. TLS encryption can be enabled for SSE and HTTP.

Can I limit which tools are exposed to the LLM?

Yes. Use the --include-tags and --exclude-tags options to control which tool categories (out of 10) are registered.

Is containerization supported?

Yes. A Docker image is available from ghcr.io/itential/itential-mcp, and you can also build it locally using make container.