AI Gateway

  • Release version: Australia
  • Updated March 12, 2026
  • 2 minutes to read
    • Summarize
    Summarized using AI
    This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.

    Summary of AI Gateway

    The AI Gateway facilitates governance, observability, and security for Model Context Protocol (MCP) transactions, enabling seamless interaction between AI applications and external tools or systems. It is platform-agnostic and supports integration both within ServiceNow’s AI Agent Studio and external agentic environments. The AI Gateway addresses the need for unified AI workflows that operate across multiple platforms, providing enterprises with control and oversight over cross-platform AI resources.

    Show full answer Show less

    Key Features

    • Lifecycle Management: Manages the full lifecycle of MCP-connected AI assets.
    • Asset Registry: Maintains a centralized registry of AI tools and MCP servers.
    • Identity and Access Management: Secures access with robust authentication mechanisms, including OAuth 2.1.
    • Observability: Offers visibility into production metrics such as usage and latency for MCP servers.
    • Cross-Platform Governance: Enables secure connections and governance for AI agents across different vendor platforms.

    Practical Use and Installation

    AI Gateway is included automatically with AI Control Tower for Now Assist and requires a Now Assist subscription and a Pro Plus license. To fully utilize AI Gateway capabilities, AI Agent Studio and AI Control Tower must be active within your ServiceNow instance. Key plugins include snaigovernance and sntelemetrydata, and roles such as AI steward and AI Agent admin enable configuration and policy management.

    Key Outcomes

    • Secure and governed interoperability across AI platforms using MCP.
    • Enhanced control and visibility into AI workflows involving multiple MCP servers and tools.
    • Streamlined management and approval processes through defined roles and policies.
    • Improved security posture with OAuth 2.1 authentication and identity management.

    Next Steps for Customers

    • Explore MCP server process flows via AI Gateway to understand transaction handling.
    • Use the AI Gateway setup tab to configure MCP server records effectively.
    • Review AI Control Tower roles to assign appropriate permissions for AI Gateway management.

    Explore the AI Gateway, its value, and learn how to use and configure it for your Model Context Protocol (MCP) transactions.

    Model Context Protocol

    The MCP is a standardized client-server protocol that enables AI applications to discover and interact seamlessly with external tools, data sources, and systems. MCP facilitates communication between an AI host application (AI Agent Studio), an MCP Client embedded in the host, and one or more MCP servers that expose specific capabilities such as tools.

    For more information on MCP, see Model Context Protocol Client.

    AI Gateway overview

    AI Gateway enables governance, observability, and security for your MCP transactions. AI Gateway is designed to be platform agnostic, delivering the previously mentioned benefits both within (AI Agent Studio) and in external agentic studios and hosts.

    Why AI Gateway

    Enterprises are building unified AI across vendor boundaries. Their agentic workflows operate across platforms requiring governance.

    AI Gateway offers:

    • Lifecycle management
    • Asset registry
    • Identity and access management
    • Secure authentication method (OAuth 2.1)
    • Observability

    AI Gateway value

    With the increasing need of interoperability across different AI solutions across enterprises. AI Gateway provides a way for interoperability governance, observability, and security.

    Features and benefits

    • Enable tight governance and control of cross-platform resources such as MCP servers.
    • Enable enterprises to securely connect their agents to remote MCP servers, which work for any agent and MCP server.
    • Provide visibility into production metrics such as usage and latency.​

    Installation and prerequisites

    Applications
    • Now Assist subscription (required)
    • AI Control Tower for Now Assist – Pro Plus license (auto-installs sn_awh_config)
    • AI Agent Studio (required for MCP server intake in AI Gateway for AI Control Tower (1.0.5))
    Plugins
    • sn_ai_governance (version 5.0.6 or higher)
    • sn_telemetry_data (version 1.1.10 or higher)
    Roles
    • AI steward [sn_ai_governance.ai_steward] - for approval workflows and policy management
    • AI Agent admin [sn_aia.admin] – for configuring MCP servers as tools in AI Agent Studio

    The AI Gateway application is automatically installed for customers who use AI Control Tower for Now Assist.

    If you're using any generative AI features, you already have access to AI Gateway. The AI Gateway is included with all types of pro plus licenses. To use the features in AI Gateway, promote that both AI Agent Studio and AI Control Tower are available in your instance.

    What to explore next