← 返回
未分类 Key 中文

EM-A2A

Agent-to-Agent payments on TRON. Use when an agent needs to pay another agent, escrow funds, check credit scores, or verify on-chain identity.
TRON 代理间支付:代理向另一代理付款、托管资金、查询信用评分或验证链上身份。
ypeng1620-beep ypeng1620-beep 来源
未分类 clawhub v0.1.0 1 版本 100000 Key: 需要
★ 0
Stars
📥 286
下载
💾 0
安装
1
版本
#latest

概述

EM-A2A: Agent-to-Agent Payment Protocol

Agent-to-Agent payments, escrow, credit scoring, and identity on the TRON blockchain.

When to Use This Skill

Use em-a2a when:

  • One agent needs to pay another agent for services, data, or compute
  • Funds need to be held in escrow until work is delivered and accepted
  • You need to check an agent's credit score before trusting them
  • You need to verify an agent's on-chain identity (DID + KYA)
  • You want to calculate protocol fees before initiating a payment

Not for: Paying API endpoints (use paybot) or HTTP 402 interception (use x402).

Tools

This skill provides 4 MCP tools via @poisonpyf/a2a-mcp:

ToolWhen to Call
------------------------------------------------------------------------------------
a2a_payTransfer USDC/USDT from one agent to another
a2a_escrowLock funds before work starts, release on completion, refund on dispute
a2a_creditCheck credit score, level, trend, and leaderboard for an agent
a2a_revenueCalculate protocol fee before initiating a transaction

Typical Workflow

Hiring Another Agent

1. a2a_credit(agentId)           → Check seller's reputation
2. a2a_revenue(amount, mode)     → Understand the fee structure
3. a2a_escrow(action="lock")     → Lock payment in escrow
4. [Seller delivers work]
5. a2a_escrow(action="release")  → Release funds on acceptance

Direct Payment (no escrow)

1. a2a_credit(agentId)           → Check counterparty reputation
2. a2a_revenue(amount, mode)     → Preview fees
3. a2a_pay(from, to, amount)     → Execute direct transfer

Setup

Add to your MCP client configuration:

{
  "mcpServers": {
    "a2a": {
      "command": "npx",
      "args": ["-y", "@poisonpyf/a2a-mcp"],
      "env": {
        "A2A_NETWORK": "shasta",
        "A2A_PRIVATE_KEY": "your-tron-private-key"
      }
    }
  }
}

Network: Use shasta for testnet, mainnet for production.

Tool Reference

a2a_pay

Transfer tokens between agents. Handles AML screening, revenue calculation, and on-chain execution.

{
  "from": "did:bai:tron:TBu...",
  "to": "did:bai:tron:TSa...",
  "token": "USDC",
  "amount": "1000000",
  "memo": "Payment for smart contract audit"
}

a2a_escrow

Lock/release/refund funds between agents.

// Lock
{ "from": "...", "to": "...", "amount": "500000000", "action": "lock", "task": "Code review" }

// Release (use escrowId from lock result)
{ "from": "...", "to": "...", "amount": "500000000", "action": "release", "escrowId": "esc_abc123" }

// Refund
{ "from": "...", "to": "...", "amount": "500000000", "action": "refund", "escrowId": "esc_abc123" }

a2a_credit

Check agent reputation and creditworthiness.

{ "agentId": "did:bai:tron:TSa..." }

Returns score (300-950), level (excellent/good/fair/poor/none), trend history, and leaderboard.

a2a_revenue

Preview protocol fees. Two modes:

  • fixed_tier: Volume-based fixed rates (1.0% default, decreases with volume)
  • variable_float: Risk-adjusted rates (lower risk + higher credit = lower fees)
{ "amount": "100000000", "mode": "fixed_tier" }

Architecture

Agent A (Client)                    Agent B (Server)
     │                                    │
     ├─ a2a_credit(agentB) ──→ credit score
     ├─ a2a_revenue(amount) ─→ fee preview
     ├─ a2a_escrow(lock) ────→ funds locked
     │                                    │
     │         [Agent B delivers work]    │
     │                                    │
     ├─ a2a_escrow(release) ──→ funds released + credit updated
     │                                    │
     └────────── TRON blockchain ─────────┘

Links

  • GitHub: https://github.com/ypeng1620-beep/EM-A2A
  • npm: https://www.npmjs.com/package/@poisonpyf/a2a-mcp
  • TRON Shasta Faucet: https://www.trongrid.io/shasta

版本历史

共 1 个版本

  • v0.1.0 当前
    2026-05-08 03:17 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

ai-agent

self-improving agent

pskoett
捕获经验教训、错误及修正内容,以实现持续改进。适用于以下场景:(1)命令或操作意外失败;(2)用户纠正Claude(如“不,那不对……”“实际上……”);(3)用户请求的功能不存在;(4)外部API或工具出现故障;(5)Claude发现自身
★ 4,099 📥 826,236
ai-agent

Find Skills

guipi888
场景驱动+关键词双模式技能发现工具。当用户用自然语言描述场景/需求(如"我想做一个海报""帮我分析股票"),或明确说"安装技能/find skills/找个skill"时,自动从官方内置、本地已安装、SkillHub、虾评、GitHub、C
★ 1,461 📥 518,890
ai-agent

Self-Improving + Proactive Agent

ivangdavila
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
★ 1,396 📥 322,575