You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+58-10Lines changed: 58 additions & 10 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -104,23 +104,71 @@ See [examples/](examples/) for 9 industry-specific policy templates.
104
104
105
105
---
106
106
107
-
## Ecosystem Positioning
107
+
## APoP's Unique Position
108
108
109
-
APoP is the **authorization layer**that complements the broader agentic protocol ecosystem:
109
+
APoP is the **missing consent & authorization layer**in the agentic web stack. Every protocol above assumes the agent has the right to act. APoP is what makes that assumption **explicit, verifiable, and enforceable**.
|**[MCP](https://modelcontextprotocol.io/)** (Model Context Protocol) | Defines how agents invoke tools and access context | APoP gates _which_ MCP tools an agent may call. `interop.mcpServerUrl` links to MCP endpoint. |
114
-
|**[A2A](https://google.github.io/A2A/)** (Agent-to-Agent Protocol) | Defines how agents communicate with each other | APoP enforces access rules _before_ A2A delegation. `interop.a2aAgentCard` links to Agent Card. |
115
-
|**[WebMCP](https://anthropic.com/research/webmcp)**| Exposes browser-side tools via `navigator.modelContext`| APoP determines _if_ a WebMCP tool may execute. `interop.webmcpEnabled` declares support. |
116
-
|**[AP2](https://protocols.ai/ap2)** (Agent Protocol v2) | Agent lifecycle and identity using Verifiable Credentials | APoP supports AP2's VC-based verification via `verifiable-credential` method. |
117
-
|**[APAAI](https://apaai.org/)**| Accountability and audit logging for agent actions | APoP works alongside APAAI for compliance. `interop.apaaiEndpoint` links to audit endpoint. |
|**WebMCP** (Google/Microsoft) | Browser-native tool contracts for agent-website interaction | No consent management; assumes permission already granted |
152
+
|**MCP** (Anthropic) | Server-side tool/data integration for LLMs | No website-level policies; focuses on backend services |
153
+
|**A2A** (Agent-to-Agent) | Inter-agent communication standard | No resource owner authorization; agents need permission to access underlying resources |
154
+
|**AP2** (Agent Payments) | Payment flows for agent transactions | Doesn't address whether agent should access resource before payment |
155
+
|**APAAI** (Auditing Protocol) | Post-hoc agent action auditing | Reactive, not preventive; APoP provides proactive control |
156
+
|**UCP** (Universal Commerce) | Standardized e-commerce for agents | No access control; APoP gates which agents can use commerce tools |
157
+
158
+
### Interoperability
159
+
160
+
APoP links directly to these protocols via the `interop` field in your policy:
|`interop.ucpCapabilities`| Your UCP commerce profile |
168
+
|`interop.apaaiEndpoint`| Your APAAI audit endpoint |
169
+
170
+
---
171
+
124
172
## Why It Matters
125
173
126
174
AI agents are already browsing, summarizing, and interacting with the web — but websites have no standardized way to express **consent or control**. APoP introduces a simple, open mechanism that brings **balance** between innovation and ownership.
0 commit comments