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
ch. 04, Layer 04: Runtime Controls & Observability - Chapters
- ch. 04, The Stack · ch. 05, Patterns · ch. 23, AI Agents
- Contrast with
- A2A (Agent2Agent protocol)
- Source
- 1 numbered reference, listed below
Where it is used
4 chapters of the Body of Knowledge use the term. Each link opens the first section that does.
Mentions as a table
| Chapter | Mentions | Cross-referenced |
|---|---|---|
| 00 Preface | 0 | No |
| 01 Definition | 0 | No |
| 02 Why Now | 0 | No |
| 03 Values & Principles | 0 | No |
| 04 The Stack | 4 | Yes |
| 05 Patterns | 0 | Yes |
| 06 The Role | 1 | No |
| 07 Maturity Model | 0 | No |
| 08 Regulatory Map | 0 | No |
| 10 Reading List | 1 | No |
| 11 AI Defined | 0 | No |
| 12 Governance Program | 0 | No |
| 13 Risk Management | 0 | No |
| 14 Development | 0 | No |
| 15 Deployment | 0 | No |
| 16 Fairness & XAI | 0 | No |
| 17 Incidents | 0 | No |
| 18 EU AI Act | 0 | No |
| 19 Privacy & AI | 0 | No |
| 20 Existing Law | 0 | No |
| 21 AI Laws Worldwide | 0 | No |
| 22 Principles & Standards | 0 | No |
| 23 AI Agents | 17 | Yes |
- 04 · The Stack Layer 04: Runtime Controls & Observability 4 mentions
- 06 · The Role Skills, by workflow 1 mention
- 10 · Reading List Regulation and standards 1 mention
- 23 · AI Agents The agent registry 17 mentions
Patterns that use this term
2 pattern pages use the term, most mentions first.
- Agent Identity & Scoped Credentials 3 mentions
- Sanctioned AI Gateway 1 mention
Related terms
Neighbourhood as a table
| Family | Item | Relation |
|---|---|---|
| Related terms | CIMD | Related |
| Related terms | Guardian agent | Related |
| Related terms | Prompt injection | Related |
| Related terms | Token passthrough | Related |
| Related terms | Workload identity | Related |
| Contrast with | A2A (Agent2Agent protocol) | Contrast |
| Patterns using it | Agent Identity & Scoped Credentials, 3 mentions | Uses the term |
| Patterns using it | Sanctioned AI Gateway, 1 mention | Uses the term |
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)
Definitions of legal terms paraphrase the cited text, which governs. Dated statements are as of .