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 5 GAGE programs, which carry 10 distinct definitions of it. The wording above is taught in Certified AI Transformation Professional (CATP).
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.
The open specification Anthropic released in November 2024 for how an AI agent connects to external tools and data sources, adopted by OpenAI and Google DeepMind within about six months, making an agent's actual tool connections a more inspectable, auditable fact for a security or procurement review.
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.
Where it is taught
The exact lessons this term appears in. The first module of every program is free with a free account.
- Agentic vs. Traditional AI: What Changed · AI Fundamentals, Certified AI Practitioner: Workplace Foundations
- Using AI Tools: Automation, Chatbots, and Analytics · Practical AI Workflow Design and Prompt Engineering, Certified AI Practitioner: Workplace Foundations
- Integrating AI into Existing Workflows · Practical AI Workflow Design and Prompt Engineering, Certified AI Practitioner: Workplace Foundations
- Professional Prompt Engineering as Communication Competency · Practical AI Workflow Design and Prompt Engineering, Certified AI Practitioner: Workplace Foundations
- Attacks on the Collective · Multi-Agent Governance, Certified Agentic AI Governance Professional (CAAGP)
- The agent at the door: an AI agent requests database credentials, and you decide · Access and the Keys, Certified AI Data Governance Professional (CADGP)
- The Emerging Frontier: Agents, Synthetic Data, Edge AI, and What Comes Next · Technical Credibility Deep Dive, The AI Lobbyist: Certified AI Policy Strategist
- The AI Technology Stack Decoded · AI Literacy for Decision Makers, Certified AI Transformation Professional (CATP)
- Vendor Management and Contracts · Technology, Platforms and Vendors, Certified AI Transformation Professional (CATP)
- Frontier AI, Autonomous Agents and Emerging Paradigms · Risk, Resilience and Frontier AI, Certified AI Transformation Professional (CATP)
Where it shows up at work
A definition is where Model Context Protocol (MCP) starts. The lessons above teach it inside the competencies below, which are what job descriptions ask for and what the GAGE credential records. Every link here is drawn from the same careers map that builds a role's readiness check.
Governs AI agents that take actions: tool access, least privilege, interruptibility, cascading actions and accountability for what an agent did.
3 lessons on this page teach it as a primary outcome.
Decides where AI should be used, where it should not, and which use cases create measurable value, tied to the organization's priorities.
3 lessons on this page teach it as a primary outcome.
Briefs a model like a good manager: context, constraints, examples, verification, and knows when to stop delegating.
3 lessons on this page teach it as a primary outcome.
Roles that hire for it
Each role page shows the full competency set, what the seat decides, and a readiness check against your own evidence.
- Chief Technology Officer, AI engineering editionneeds working knowledge
- Chief Information Security Officer, AI security focusneeds it at depth
- AI Security Architectneeds it at depth · 8 open postings this week
- Chief AI Officerneeds it at depth
- Chief Information Officer, technology leadership editionneeds it at depth
- VP of AI Governance and Ethicsneeds working knowledge
How job descriptions say it
Postings rarely use the textbook word. These are the phrases the careers map reads as asking for the competencies above.
Where the frameworks place it: IMDA Model AI Governance Framework for Agentic AI; NIST AI RMF.
One interview question about it
An agent can send emails and update records. What may it touch, what needs a human, and how do you prove afterwards what it did?
Asked of candidates for agentic ai controls and authorization boundaries. Answering it in your own words is exactly how a GAGE topic is passed, and the credential records the pass where an employer can check it.
If you come from another field
Some backgrounds already carry this competency, and the readiness check gives credit for it.
- A business, MBA or technology management degree carries it as a claim to back up: Strategy and opportunity triage are the core of the degree.
- A computer science or software engineering degree carries it as work you can show: Prompting and tool workflows are already in your daily work.
Terms it appears with
Not an alphabetical neighbourhood: these are the terms taught in the same lessons, ranked by how often they appear together.