Model Context Protocol

Overview

Model Context Protocol (MCP) is a protocol for connecting AI models and agents to external tools, data sources, and application servers in a more standardized way. Instead of building one-off integrations for every model-tool pairing, MCP creates a common interface that allows AI systems to discover available capabilities and interact with them more reliably.

For AI Product Managers, MCP matters because it sits at the intersection of agent design, tool orchestration, and enterprise integration. As products increasingly depend on models being able to retrieve data, trigger actions, and work across SaaS platforms, a protocol like MCP can reduce integration complexity, improve interoperability, and make agent experiences more scalable. Newsletter mentions specifically highlighted two important themes: dynamic discovery of MCP servers and large reductions in token usage, both of which have direct implications for cost, performance, and product architecture.

Key Developments

• 2026-01-10 — Phil Schmid introduced mcp-cli, an open-source CLI for dynamic discovery of Model Context Protocol servers. The newsletter noted that it could reduce MCP token usage by 99% while improving AI agent tool interactions.
• 2026-03-24 — Teun Rutten highlighted HubSpot’s developer ecosystem, especially its use of Model Context Protocol to let AI tools such as Cursor and Claude interact directly with HubSpot data.

Relevance to AI PMs

• Designing scalable agent integrations: MCP offers a more reusable pattern for connecting models to tools and systems, which can reduce engineering overhead when expanding agent capabilities across multiple products or partners.
• Improving cost and latency: The mention of dynamic server discovery and dramatically lower token usage suggests that MCP implementations can materially affect inference cost, context size, and responsiveness—key levers for PMs managing margins and UX.
• Enabling ecosystem strategy: MCP can make it easier for external AI tools and agents to work with your platform. For PMs, that creates opportunities around developer adoption, partner integrations, and turning proprietary product data into agent-accessible functionality.

Related

• HubSpot — Cited as an example of a platform using MCP so AI tools can interact directly with product data.
• Cursor — Mentioned as one of the AI tools that can use MCP-enabled connections to access external systems like HubSpot.
• Claude — Another AI assistant referenced in the context of MCP-based interaction with HubSpot data.
• mcp-cli — An open-source command-line tool focused on dynamic discovery of MCP servers and reducing token overhead.
• AI agent — MCP is highly relevant to agent architectures because agents often need standardized ways to discover tools, retrieve context, and take actions across systems.