Model Context Protocol (MCP)
An open standard that lets an AI agent connect to tools, data, and other systems through one common interface. Donated by Anthropic to the Agentic AI Foundation (a directed fund under the Linux Foundation) in December 2025, it became a widely adopted, vendor-neutral standard, lowering lock-in and shifting the governance focus to access design.
Defined in 4 GAGE programs, which carry 9 distinct definitions of it. The wording above is taught in Business AI Transformation.
How each discipline defines it
The same term does different work depending on who is using it. These are the definitions as each program teaches them, unedited.
An open standard that lets an AI agent connect to tools, data, and other systems through one common interface. Donated by Anthropic to the Agentic AI Foundation (a directed fund under the Linux Foundation) in December 2025, it became a widely adopted, vendor-neutral standard, lowering lock-in and shifting the governance focus to access design.
an open, vendor-neutral standard (introduced by Anthropic in late 2024, adopted across major vendors by 2025) that lets AI agents connect to external tools and data in a common way; the practical backbone of agent tool use and interoperability.
A protocol governing how a single agent discovers and calls external tools, described by the CSA Addendum as the sibling protocol to A2A; MCP governs agent-to-tool communication where A2A governs agent-to-agent communication. (see Topic 8.5)
An open standard, introduced by Anthropic in November 2024, for connecting AI assistants to external tools and data sources through a defined set of specific, callable actions rather than direct, unrestricted database or file-system access.
An open standard for connecting AI tools to data sources and other systems, adopted by Anthropic, OpenAI, Google DeepMind, and Microsoft and placed under Linux Foundation governance in December 2025; reduces integration effort and exit cost.
Where it is taught
The exact lessons this term appears in. The first 7 topics of every program are free with a free account.
- Agentic vs. Traditional AI: What Changed · AI Fundamentals, AI Literacy & Professional Conduct
- Using AI Tools: Automation, Chatbots, and Analytics · Practical AI Workflow Design and Prompt Engineering, AI Literacy & Professional Conduct
- Integrating AI into Existing Workflows · Practical AI Workflow Design and Prompt Engineering, AI Literacy & Professional Conduct
- Professional Prompt Engineering as Communication Competency · Practical AI Workflow Design and Prompt Engineering, AI Literacy & Professional Conduct
- Attacks on the Collective · Multi-Agent Governance, Agentic AI Governance: Applied Mastery
- The agent at the door: an AI agent requests database credentials, and you decide · Access and the Keys, AI Data Governance: The Data Chair
- The AI Technology Stack Decoded · AI Literacy for Decision Makers, Business AI Transformation
- Vendor Management and Contracts · Technology, Platforms and Vendors, Business AI Transformation
- Frontier AI, Autonomous Agents and Emerging Paradigms · Risk, Resilience and Frontier AI, Business AI Transformation
Terms it appears with
Not an alphabetical neighbourhood: these are the terms taught in the same lessons, ranked by how often they appear together.