Enterprise AI Gateway & MCP Gateway | Truefoundry

# TrueFoundry > TrueFoundry is an enterprise-grade AI Gateway that encompasses an LLM Gateway, MCP Gateway, and Agent Gateway, enabling enterprises to securely connect, observe, and govern access to models, tools, guardrails, and agents from a single control plane. The AI Gateway enables agentic workloads that are secure, efficient, and future-safe through unified and composable connections across providers. Beyond the gateway layer, TrueFoundry enables organizations to deploy and train custom LLMs on GPUs, host MCP servers, and run custom agents, all through a Kubernetes-native interface. It supports on-premise and VPC installations for both AI Gateway and deployment environments. TrueFoundry ensures enterprise-grade compliance with SOC 2, HIPAA, and ITAR standards. With built-in autoscaling, caching, and resource optimization, TrueFoundry empowers organizations to build, deploy, and govern AI systems securely, efficiently, and on a future-safe stack. --- ## Core Products & Services ### AI Gateway - **What it does:** TrueFoundry's AI Gateway is a unified proxy layer that sits between applications and LLM providers, MCP servers, and agents. It provides a single endpoint for accessing 1000+ LLMs, enforcing governance, and observing all AI traffic across an organization. It extends beyond LLM routing to cover tools (via MCP) and agents (via the A2A protocol), creating a single control plane for all AI interactions. - **Who uses it:** Enterprise platform teams, engineering teams and leaders, ML teams and IT security teams who need to standardize and govern AI access across multiple teams and environments. - **Key features:** - Unified API access to 1000+ LLMs across OpenAI, Anthropic, Google Gemini, AWS Bedrock, Azure OpenAI, Groq, Mistral, Cohere, and self-hosted models - Multi-model routing with load balancing by weight, latency, or priority - Automatic fallback chains and retries across model providers - Fine-grained Role-Bas