Model Context Protocol

The Model Context Protocol (MCP) is an open standard, introduced by Anthropic in late 2024, that lets AI assistants connect to outside tools, databases, and business systems through a common interface. Because each connection can give an AI agent the ability to read files, send messages, or change records, MCP servers effectively extend what the AI can do inside the organization. Compliance and risk teams should treat every MCP connection as a new access path that needs the same scrutiny as an employee account, covering who approves it, what data it can reach, and how its actions are logged.

2 items

Corporate PolicyUS2026-10-23

Walmart's Agent Gateway Sets Industry Benchmark for Agentic Commerce Controls

Walmart has opened its shopping platform to third-party AI agents through a new Agent Gateway built on the Model Context Protocol. This standard allows AI systems to connect with external services. The retailer has published explicit governance terms requiring agents to stay within shopper intent, prohibiting payment method changes, and limiting data access to only what each task requires. Enterprise controls include mandatory purchase approval by default, configurable spending limits, segregated purchase histories, and the ability to revoke agent access at any time.

agentic AI Model Context Protocol data minimization consumer AI policy procurement controls Walmart spending limits vendor governance

InsightGlobal2026-06-13

AI Governance Institute Publishes Open-Source MCP Server for Automating Governance Controls

AI Governance Institute released an open-source MCP server for Claude Code and other compatible clients. It provides safety screening (SAF-001), risk classification (HOC-001), and automated red-teaming (SAF-005) for developers and compliance teams.

open source MCP Model Context Protocol governance automation safety screening risk classification red-teaming Claude Code developer tools compliance tooling