---
title: "MCP"
description: "Model Context Protocol: an open protocol for connecting AI applications to tools and data sources; its 2026 specification adds OAuth 2.1 resource-server patterns and issuer-bound credentials for…"
canonical: https://aigovernanceengineer.com/glossary/mcp
author: "Jorge García Aibar"
license: "CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)"
doi: https://doi.org/10.5281/zenodo.22956197
version: "0.5.0"
updated: 2026-09-25
---

# MCP

Model Context Protocol: an open protocol for connecting AI applications to tools and data sources; its 2026 specification adds OAuth 2.1 resource-server patterns and issuer-bound credentials for agent authorisation [1]. It secures the hop between one client and one server; which agent sits behind the client is for a workload identity to say.

- Developed in: [ch. 23, MCP authorization as of 2026-07-28](https://aigovernanceengineer.com/bok/governing-agents#mcp-authorization-as-of-2026-07-28); [ch. 04, Layer 04: Runtime Controls & Observability](https://aigovernanceengineer.com/bok/the-stack#layer-04-runtime-controls--observability)
- Chapters: [ch. 04, The Stack](https://aigovernanceengineer.com/bok/the-stack) · [ch. 05, Patterns](https://aigovernanceengineer.com/bok/patterns) · [ch. 23, AI Agents](https://aigovernanceengineer.com/bok/governing-agents)
- Contrast with: [A2A (Agent2Agent protocol)](https://aigovernanceengineer.com/glossary/a2a-agent2agent-protocol)
- In the glossary chapter: https://aigovernanceengineer.com/bok/glossary#t-mcp

## Sources

[1] Model Context Protocol specification 2026-07-28 (OAuth 2.1 resource servers; Client ID Metadata Documents; issuer-bound credentials). Anthropic / MCP. 2026-07-28. https://blog.modelcontextprotocol.io/posts/2026-07-28/ (verified: primary)