--- 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 --- # Extending AI with external systems and providers # Extending AI with external systems and providers {#ariaid-title1} Release version: Brazil Updated September 10, 2026 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read Summarize ![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) 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 Extending AI with external systems and providers ServiceNow's AI Platform enables integration with external large language model (LLM) providers and tools beyond the platform, offering flexibility in choosing AI services that fit your organizational needs. This capability allows you to extend AI functionalities by connecting to third-party LLMs and external tools using the Generative AI Controller and the Model Context Protocol (MCP). Show full answer Show less ## Key Features * **Generative AI Controller:** Automatically installed with AI applications, it integrates third-party generative AI providers such as OpenAI, Azure OpenAI, Google Cloud AI Studio and Vertex, IBM watsonx, and Amazon Bedrock. It supports use cases in Workflow Studio flows, Virtual Agent topics, and scripting (e.g., background scripts and business rules). * **Model Context Protocol (MCP) Client:** A standardized client-server protocol that enables AI applications (like AI Agent Studio) to discover and interact with external tools, data sources, and services. MCP Client manages communication with MCP servers, allowing AI agents to perform diverse tasks by connecting to multiple external tools. * **MCP Server Console:** Provides a console within your ServiceNow instance to create and configure MCP servers that expose specific tools and functionalities to external clients securely via OAuth 2.0. You can tailor servers and tools to different use cases (e.g., HR or IT workflows) or clients, enabling external AI applications such as Microsoft Copilot or AWS Claude to use your instance's capabilities. ## Key Outcomes * Enable seamless integration of external LLM providers and AI tools within ServiceNow workflows, virtual agents, and custom scripts. * Expand AI agent capabilities by connecting to multiple external tools and services to perform complex and varied tasks. * Expose ServiceNow instance tools securely to external AI applications, allowing users to prompt for actions or data retrieval, such as summarizing incident lists. * Administrators can monitor MCP servers and tool usage through AI Gateway in AI Control Tower, supporting governance and operational oversight. Connect to large language model (LLM) providers through the Generative AI Controller and integrate AI agents with external tools and services using the Model Context Protocol (MCP). The ServiceNow AI Platform works with external systems and model providers, giving you flexibility to choose the LLM providers that meet your requirements and connect AI agents to tools and services beyond the platform. ## Generative AI Controller {#platai-extending-ai-external-systems-providers__section_lcs_xz5_rkc} The Generative AI Controller integrates third-party generative AI into the platform. The controller supports external LLM providers, including OpenAI, Azure OpenAI, Google Cloud (AI Studio and Vertex), IBM watsonx, and Amazon Bedrock. These capabilities are available in Workflow Studio flows, Virtual Agent topics, and scripting such as background scripts and business rules. The Generative AI Controller is installed automatically with any AI application. To bring third-party LLM providers such as OpenAI, Google, and Amazon Bedrock into flows, Virtual Agent, and scripts, see [Generative AI Controller](https://www.servicenow.com/docs/5PNc85yCL5Mdppm8apxKqQ "Use Generative AI Controller to integrate your ServiceNow applications with third-party large language models (LLMs) and manage how generative AI requests are governed, protected, and logged."). ## MCP Client {#platai-extending-ai-external-systems-providers__section_mcs_xz5_rkc} The Model Context Protocol (MCP) is a standardized client-server protocol that enables AI applications to discover and interact seamlessly with external tools, data sources, and services. MCP Client manages communication between a host application, such as AI Agent Studio, and one or more MCP servers that expose specific capabilities. MCP tools enable you to connect your AI agent with a wide variety of external tools and add multiple MCP tools to an AI agent to perform a broader range of tasks. To connect your AI agents to external tools, data sources, and services through the Model Context Protocol, see [Model Context Protocol Client](https://www.servicenow.com/docs/y3AomlTl4lo9aJe22uMb_g "The ServiceNow Model Context Protocol Client (MCP Client) enables you to access the Model Context Protocol tools that are hosted externally and published using an MCP Server in the ServiceNow AI Agent Studio."). ## MCP Server Console {#platai-extending-ai-external-systems-providers__section_ncs_xz5_rkc} MCP Server Console console lets you create MCP servers on your instance and configure the tools they expose to external clients. Tools define which functionality and data a server makes available and the actions that can be performed on the instance. You can create tools based on existing capabilities such as generative AI skills, and you can create multiple servers that expose different tools for different use cases, such as HR or IT workflows, or for different clients. Any AI application, such as Microsoft Copilot or AWS Claude, can call a server using OAuth 2.0 authentication and get a list of available tools. Employees using the MCP Client can then prompt the server for information from the instance or to perform an action, such as summarizing a list of recently closed incidents or cases. Note: With AI Gateway in AI Control Tower, administrators can monitor MCP Server Console and access and view metrics for servers and their tools. To create MCP servers that expose your instance's tools, including generative AI skills, to external clients such as Microsoft Copilot or AWS Claude, see [MCP Server Console](https://www.servicenow.com/docs/eI0asNG5oVrwkv2I18Zmtw "MCP Server Console enables secure and governed access to functionality on a ServiceNow instance for AI applications with Model Context Protocol (MCP) servers. MCP servers extend ServiceNow AI Platform functionality into any external MCP client and employee experience over the Model Context Protocol.").