Obot MCP Gateway
Obot is an open-source AI infrastructure platform and Model Context Protocol (MCP) gateway that gives organizations a centralized control plane for discovering, onboarding, managing, securing, and scaling MCP servers, services that connect large language models and AI agents to enterprise systems, tools, and data. It bundles an MCP gateway, catalog, admin console, and optional built-in chat interface into a modern interface that integrates with identity providers (e.g., Okta, Google, GitHub) to enforce access control, authentication, and governance policies across MCP endpoints, ensuring secure, compliant AI interactions. Obot lets IT teams host local or remote MCP servers, proxy access through a secure gateway, define fine-grained user permissions, log and audit usage, and generate connection URLs for LLM clients such as Claude Desktop, Cursor, VS Code, or custom agents.
Learn more about Obot MCP Gateway
Amazon SageMaker
Amazon SageMaker is an advanced machine learning service that provides an integrated environment for building, training, and deploying machine learning (ML) models. It combines tools for model development, data processing, and AI capabilities in a unified studio, enabling users to collaborate and work faster. SageMaker supports various data sources, such as Amazon S3 data lakes and Amazon Redshift data warehouses, while ensuring enterprise security and governance through its built-in features. The service also offers tools for generative AI applications, making it easier for users to customize and scale AI use cases. SageMaker’s architecture simplifies the AI lifecycle, from data discovery to model deployment, providing a seamless experience for developers.
Learn more about Amazon SageMaker
DeployStack
DeployStack is an enterprise-focused Model Context Protocol (MCP) management platform designed to centralize, secure, and optimize how teams use and govern MCP servers and AI tools across organizations. It provides a single dashboard to manage all MCP servers with centralized credential vaulting, eliminating scattered API keys and manual local config files, while enforcing role-based access control, OAuth2 authentication, and bank-level encryption for secure enterprise usage. It offers usage analytics and observability, giving real-time insights into which MCP tools teams use, who accesses them, and how often, along with audit logs for compliance and cost-control visibility. DeployStack also includes token/context window optimization so LLM clients consume far fewer tokens when loading MCP tools by routing through a hierarchical system, allowing scalable access to many MCP servers without degrading model performance.
Learn more about DeployStack
agentgateway
agentgateway is a unified gateway platform designed to secure, connect, and observe an organization’s entire AI ecosystem. It provides a single point of control for LLMs, AI agents, and agentic protocols such as MCP and A2A. Built from the ground up for AI-native connectivity, agentgateway supports workloads that traditional gateways cannot handle. The platform enables controlled LLM consumption with strong security, usage visibility, and budget governance. It offers full observability into agent-to-agent and agent-to-tool interactions. agentgateway is deeply invested in open source and is hosted by the Linux Foundation. It helps enterprises future-proof their AI infrastructure as agentic systems scale.
Learn more about agentgateway