Install
$ agentstack add mcp-jtone123-web4-agent-protocol ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Welcome to the Web4 Agent Protocol Wiki
> Universal REST API MCP with built-in authentication and payments
!!! DRAFT !!! TBD
The Web4 Agent Protocol redefines the user-web interface. It is a forward-looking, open standard designed to create a new, symbiotic relationship between users, their AI Agents (powered by LLMs), and the open web.
The Problem
Modern LLMs are powerful, but they often act as a barrier between users and websites. They aggregate information, which is useful, but they lack the ability to perform meaningful actions on the user's behalf. This limits their utility and threatens the economic models that support the web's creators.
The Solution: A New User-Web Experience
The Web4 Agent Protocol integrates with the existing web rather than replacing it, providing a standardized framework for websites to securely expose their core functionality.
This transforms AI Agents from simple information retrievers into powerful personal assistants. A user can now not only ask about flights but also book them, not just read a review but also buy the product—all through a single, secure, conversational interface.
Search engines like Google and Bing can index the public [web4 agent definition file](/docs/FullExampleDefinition_File.md), allowing them to act as an mcp-client on the user's behalf. This enables direct interaction with websites through a chatbot or from the search results page.
Envisioned as an evolution—akin to MCP 2.0—for seamless daily web interactions, the protocol will integrate authentication and payment capabilities into the agent's core. This creates a unified experience where the agent securely manages user identity and transactions across services, becoming a trusted assistant for the user's entire web presence.
Benefits of the Web4 Agent Protocol
- For Users: Enjoy a seamless, unified experience. Buy products, book services, and access content from any website through your AI Agent, all while using your existing website accounts securely.
- For Publishers: Create new, direct revenue streams through microtransactions and optimized advertising, independent of site traffic. Integration is simplified by placing an intelligent gateway in front of your existing API, not by rewriting it.
- For Advertisers: Pay only for verifiably engaged user attention in a transparent, on-chain ecosystem.
Key Sections
- Core Concepts
- [1. Architecture Overview](/docs/Architecture_Overview.md)
- [2. Pillar 1: MCP Gateway & Definition](/docs/Pillar1MCPGatewayand_Definition.md)
- [3. Pillar 2: Decentralized Authorization](/docs/Pillar2Decentralized_Authorization.md)
- [4. Pillar 3: Native Microtransactions](/docs/Pillar3Native_Microtransactions.md)
- Developer Guides
- [5. Implementation (Proof of Concepts)](/docs/Implementation_POC.md)
- [6. Full Example: Definition File](/docs/FullExampleDefinition_File.md)
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: JTOne123
- Source: JTOne123/web4-agent-protocol
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.