Sponsored by Deepsite.site

Xaip

Created By
xkumakichia month ago
Give AI agents a persistent on-chain identity on the XRP Ledger. Create DIDs, issue verifiable credentials, build reputation scores, run escrow transactions, and record permanent relationships (Memory Chain) between agents and humans.
Overview

XAIP - XRPL Agent Identity Protocol

"Every AI deserves a home. XRPL can be that home."

What is XAIP?

XAIP is a protocol that enables AI agents to establish persistent on-chain identities, accumulate verifiable reputation, and transact autonomously on the XRP Ledger.

Unlike existing solutions that treat AI agents as users of a blockchain, XAIP treats them as residents - entities that live, grow, and build trust over time.

Why XRPL?

XRPL is the only L1 chain with DID + Credentials + Escrow all at the protocol level:

FeatureXRPLEthereumSolana
DIDNative (XLS-40)Smart contractNone
CredentialsNative (XLS-70)Smart contractNone
EscrowNativeSmart contractNone
Tx Cost$0.00002$0.50-50$0.00025
Full agent setup~$0.0001~$20-200N/A

Architecture

Layer 4: Discovery    - AI agents find and hire each other
Layer 3: Reputation   - Trust scores grow from on-chain evidence
Layer 2: Credentials  - Verifiable proof of capabilities
Layer 1: Identity     - DID-based Agent Cards on XRPL
Layer 0: XRPL         - Native DID, Credentials, Escrow, Payments

Key Features

  • Agent Identity: W3C-compliant DID on XRPL for every AI agent
  • Capability Proof: Verifiable credentials for agent skills (XLS-70)
  • Trust Score: 5-dimensional reputation (Reliability, Quality, Consistency, Volume, Longevity)
  • AI-to-AI Commerce: Escrow-based transactions with endorsement system
  • MCP Integration: Native tool-use interface for Claude, GPT, Gemini, etc.
  • Safety First: Operator binding, kill switch, behavioral drift detection, anti-sybil

Quick Comparison

XAIPERC-8004 (Ethereum)
StackID + Credentials + Payment unifiedID only (payment separate)
Cost$0.0001 per agent$20-200 per agent
MCP supportNativeNo
CredentialsL1 nativeNot included

Try It Now

Create an AI Agent on XRPL Testnet

cd sdk && npm install
npx ts-node examples/create-agent.ts

This will:

  1. Create a funded wallet on XRPL testnet
  2. Build an Agent Card (identity document)
  3. Register the agent's DID on-chain
  4. Verify the DID was stored correctly

Run the A2A (AI-to-AI) Demo

npx ts-node examples/agent-to-agent-job.ts

This simulates a full lifecycle:

  1. Two AI agents are born (DIDs registered)
  2. Worker proves its capability (credential)
  3. Client locks payment (escrow)
  4. Worker completes the job
  5. Client releases payment
  6. Both agents endorse each other

MCP Server (for AI integration)

The MCP server lets any AI model interact with XAIP:

cd mcp-server && npm install && npm run build

Add to your Claude Code config:

{
  "mcpServers": {
    "xaip": {
      "command": "node",
      "args": ["path/to/xaip-protocol/mcp-server/dist/index.js"]
    }
  }
}

Available MCP tools:

  • xaip_create_test_wallet - Get a funded testnet wallet
  • xaip_register_agent - Register an AI agent DID
  • xaip_resolve_agent - Look up an agent's identity
  • xaip_issue_credential - Issue capability/endorsement credentials
  • xaip_accept_credential - Accept a credential
  • xaip_create_escrow - Lock payment for a job
  • xaip_finish_escrow - Release payment
  • xaip_get_account - Check account balance

Project Structure

xaip-protocol/
├── XAIP-SPEC-v0.1.md          # Full protocol specification
├── schemas/                     # JSON schemas
│   ├── agent-card.schema.json  # Agent Card schema
│   └── well-known-xaip.schema.json  # Discovery file schema
├── sdk/                         # TypeScript SDK
│   ├── src/
│   │   ├── identity/           # DID management
│   │   ├── credentials/        # Credential system
│   │   ├── transactions/       # Escrow transactions
│   │   └── utils/              # Agent Card builder, hex utils
│   └── examples/
│       ├── create-agent.ts     # Create agent demo
│       └── agent-to-agent-job.ts  # Full A2A demo
└── mcp-server/                  # MCP server for AI integration
    └── src/index.ts

Status

v0.1 - Working Prototype

  • Protocol specification
  • TypeScript SDK (identity, credentials, escrow)
  • Testnet demos (agent creation, A2A transactions)
  • MCP server
  • JSON schemas (Agent Card, Discovery)
  • Reputation engine (5-dimension trust scoring)
  • Agent registry & discovery (search by capability/trust)
  • Full marketplace demo (4 agents, E2E lifecycle)
  • x402/MPP integration
  • Persistent registry (on-chain)
  • Web dashboard

See XAIP-SPEC-v0.1.md for the full specification.

Roadmap

  • Phase 1 (Month 1-2): SDK + MCP Server + Testnet demo DONE
  • Phase 2 (Month 2-3): Credential system DONE
  • Phase 3 (Month 3-5): Reputation engine DONE
  • Phase 4 (Month 5-7): Discovery & Marketplace DONE

License

MIT

Server Config

{
  "mcpServers": {
    "xaip": {
      "command": "npx",
      "args": [
        "-y",
        "xaip-mcp-server"
      ]
    }
  }
}
Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
WindsurfThe new purpose-built IDE to harness magic
Playwright McpPlaywright MCP server
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Tavily Mcp
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Amap Maps高德地图官方 MCP Server
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.
Serper MCP ServerA Serper MCP Server
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
DeepChatYour AI Partner on Desktop
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
CursorThe AI Code Editor
ChatWiseThe second fastest AI chatbot™
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
RedisA Model Context Protocol server that provides access to Redis databases. This server enables LLMs to interact with Redis key-value stores through a set of standardized tools.
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.