AI Summary
→ WHAT IT COVERS Craig Mc, CEO of Stacklock, explains how Model Context Protocol (MCP) functions as enterprise infrastructure for agentic AI systems, covering the four-component platform stack — runtime, registry, gateway, and control plane — and how Kubernetes provides the orchestration layer for scaling MCP servers across organizations. → KEY INSIGHTS - **MCP Platform Stack:** Enterprises need four components to operationalize MCP: a secure runtime (containerized via OCI images), a vetted registry of approved servers, a gateway providing a single endpoint across models like Claude and GPT, and a control plane for mapping servers to user groups. Building these once enables multi-model access without vendor lock-in. - **Tool Pollution Reduction:** When agents access three to four MCP servers, context windows can carry 150+ tools consuming 20,000–30,000 tokens per interaction. Replacing direct tool exposure with two proxy endpoints — find-tool and bulk-tool — reduces input token consumption by 80–90%, dramatically improving smaller model reliability from unpredictable rates to 95–97% accuracy. - **Identity and Token Exchange:** Rather than passing raw user credentials to MCP servers, enterprises should implement token exchange at the proxy layer — mapping Okta or OIDC tokens to descoped API keys or federated credentials. This pattern enforces least-privilege access, such as read-only AWS permissions, without requiring individual MCP server developers to handle authentication mechanics. - **Agentic Concurrency as Productivity Multiplier:** Stacklock's engineering team runs 5–15 simultaneous agents, each with distinct configuration and tool access, managed by one human operator. This approach produced a 60% throughput increase in a single week, enabling the team to resolve incoming issues faster than they accumulate — a pattern Craig Mc expects to transfer to non-developer knowledge workers. - **Kubernetes for MCP Orchestration:** ToolHive, an Apache 2.0 open-source project, containerizes MCP servers using OCI images, enabling file system and network endpoint restrictions per server. Kubernetes adoption for running MCP servers is growing 50% month-over-month, with millions of tool invocations now originating from Kubernetes deployments rather than developer desktops. → NOTABLE MOMENT Craig Mc describes watching a non-technical go-to-market colleague approach an engineer to configure five MCP servers — HubSpot, LinkedIn, and others — for their own workflow, signaling that MCP adoption has moved well beyond developer tooling into general business operations. 💼 SPONSORS [{"name": "Prediction Guard", "url": "https://predictionguard.com/practicalai"}] 🏷️ Model Context Protocol, Enterprise AI Infrastructure, Kubernetes, Agentic AI, AI Security