--- sourceDocument: Brazil Enable AI sourceDocumentLink: https://www.servicenow.com/docs/r/intelligent-experiences Release : - brazil ft:locale : - en-US ft:publication_title : - Brazil Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # Explore # Exploring AI Gateway {#ariaid-title1} Release version: Brazil Updated October 22, 2026 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 3 minutes to read Learn how AI Gateway governs connections between AI agents and MCP servers, where you manage it, and how an MCP server is approved for agent traffic. ## AI Gateway overview {#ai-gw-exploring__cf-exploring-parent-overview} When an agent connects to an MCP server directly, the agent holds the server's credentials, and you can't inspect or stop its traffic from one place. AI Gateway replaces those direct connections with a single governed endpoint for each server. Agents send their requests to the server's AI Gateway MCP server URL, and AI Gateway forwards each call to the MCP server. On the way, AI Gateway is designed to perform three jobs: Govern : Agents can reach only MCP servers that are managed and approved, and only the tools that are active on each server. When access management is on for a server, each client is authorized to use only the tools that its client access policies grant through AI Gateway. Control : AI Gateway handles OAuth on both sides of the connection, so agents don't see the MCP server's credentials. It scans tools for threats, checks transactions for sensitive data, and lets you turn connections off for all servers or for one. Observe : AI Gateway records each call, so you can review activity for each server and tool. ## Where you manage AI Gateway {#ai-gw-exploring__ai-gw-exploring-where-you-manage-ai-gateway} Settings that apply to every MCP server connection are on the AI Gateway settings page, at SettingsAI Gateway. Each of its tabs is described in its own topic: * [AI Gateway Overview tab](https://www.servicenow.com/docs/FW7vpobmR4T498KoBYVk1w "Use the Overview tab of the AI Gateway settings page to turn connections through AI Gateway on or off, for all MCP servers or for one server.") * [AI Gateway Tools tab](https://www.servicenow.com/docs/KWN_bfjcj8Ia33B7sC5EmA "Use the Tools tab of the AI Gateway settings page to choose whether tools are automatically deactivated after a security scan or activated after approval.") * [AI Gateway Policies tab](https://www.servicenow.com/docs/UJbezXdDanF0OpWHRv~R9w "Use the Policies tab of the AI Gateway settings page to activate the Data Sensitivity Check, which helps filter personally identifiable information in MCP traffic.") {#ai-gw-exploring__ul_ai-gw-exploring-settings-tabs} Records opened from InventoryAssetsMCP servers open on the Overview tab. Records opened by selecting a server name on the Overview tab of the settings page open on the AI Gateway tab, where per-server settings are. For the rest of the record, see [Working with MCP server records](https://www.servicenow.com/docs/9v7d9z1YIbzuR2TUTCppMg "The MCP servers tab on the AI Control Tower Inventory page provides a centralized view of MCP servers registered in your ServiceNow instance."). ## AI Gateway workflow {#ai-gw-exploring__cf-exploring-parent-workflow} An MCP server goes through these stages before agents can call its tools through AI Gateway. 1. The MCP server is added to the inventory. It can sync from AI Agent Studio, or an AI steward can add it from the MCP Catalog or AI Control Tower. 2. The AI steward moves the server to managed, which starts the Onboard playbook on the record's Lifecycle tab. 3. The AI steward completes the playbook's Assess, Build and Test, and Deploy phases. The record shows Deployed \& Approved, and its AI Gateway tab is ready for client registration. 4. The AI steward registers the clients that can connect to the server. 5. Optionally, the AI steward creates client access policies and turns on access management for the server, so that each client can use only the tools that it requires. 6. Agent owners configure their agents to use the AI Gateway MCP server URL and the client credentials. 7. The AI steward reviews the server's tools and policies, reviews its activity, and turns its connections off when needed. {#ai-gw-exploring__cf-exploring-parent-workflow-ol} ## AI Gateway benefits {#ai-gw-exploring__cf-exploring-parent-benefits} {#ai-gw-exploring__table_ai-gw-exploring-3__entry__3} | Benefit | Feature | Users | |-|-|-| | Allow agents to reach only MCP servers that an AI steward has assessed, tested, and approved. | [MCP server approval](https://www.servicenow.com/docs/hPa4Wm1KeuynX~H66V~Ixg "After you register and manage an MCP server, the AI steward moves it through the onboarding lifecycle before agents can use it.") | AI steward | | Keep MCP server credentials out of agent configurations. Agents authenticate with AI Gateway, and AI Gateway manages the credentials for the MCP server. | [Client registration](https://www.servicenow.com/docs/MBFrByx7Eh~T1QQ4td8hNw "Once an MCP server has been managed and approved, register the clients that will connect to it via AI Gateway.") | AI steward, agent owners | | Automatically deactivate tools that the security scan finds vulnerable. | [Tool automation](https://www.servicenow.com/docs/KWN_bfjcj8Ia33B7sC5EmA "Use the Tools tab of the AI Gateway settings page to choose whether tools are automatically deactivated after a security scan or activated after approval.") | AI steward | | Help filter sensitive data, such as personally identifiable information (PII), in transactions between agents and MCP servers. | [Data Sensitivity Check](https://www.servicenow.com/docs/UJbezXdDanF0OpWHRv~R9w "Use the Policies tab of the AI Gateway settings page to activate the Data Sensitivity Check, which helps filter personally identifiable information in MCP traffic.") | AI steward | | Limit each client to the tools that it requires on an MCP server. | [Client access policies](https://www.servicenow.com/docs/vdbnwpXstkbsfKFUA2BcLQ "Limit each client to the MCP server tools that it requires by turning on access management for the server and creating client access policies.") | aig_admin, AI steward | | Stop traffic to every MCP server, or to one server, without changing any agent. | [Connection controls](https://www.servicenow.com/docs/ikExhFY4VA2bh4RcIc8EXQ "Stop traffic through AI Gateway, for all MCP servers or for one server, while you investigate an issue, and turn it back on when you're done.") | AI steward | [Table 1. AI Gateway benefits] {#ai-gw-exploring__table_ai-gw-exploring-3} ## What to explore next {#ai-gw-exploring__cf-exploring-parent-links} To learn more about configuring and using AI Gateway, see: * [Configuring AI Gateway](https://www.servicenow.com/docs/yVuxmlUNpsLSrFvBQ9QDVw "Prepare your instance for AI Gateway, bring MCP servers into the inventory and approve them, and choose the settings that apply to your MCP server connections.") * [Connecting agents through AI Gateway](https://www.servicenow.com/docs/9_0XuwsnFx54Zjo0jce2JQ "Register the clients that can connect to an approved MCP server, and then configure agents to call the server through its AI Gateway MCP server URL.") * [Governing MCP server tools and data](https://www.servicenow.com/docs/C9CJVJC5Uhu9ioShIQGKfQ "Review scan results for an MCP server's tools, decide which tools agents can call, and choose the tools that the Data Sensitivity Check applies to.") * [Controlling MCP server traffic](https://www.servicenow.com/docs/7qVWjdLydBnfOiyLwqB4Zw "Turn MCP server connections off while you investigate a server, turn them back on when you're done, and review each server's activity.") * [AI Gateway reference](https://www.servicenow.com/docs/Y5P9Cke8yp8cTl49DizA3g "Reference topics provide details about the roles and system properties that apply to AI Gateway.") {#ai-gw-exploring__ul_ai-gw-exploring} *[\>]: and then