Yault AESP

xyz.yault由 yault.xyz 发布v0.2.0更新于 Oct 24, 2026

Crypto payments for the agent economy — policy-gated vault operations under human control

已验证STDIO仅桌面金融安全与监控

概览

AI 生成的概览

本地 MCP 服务器,向 AI 助手开放 Yault 加密金库操作——查询余额、充值、赎回与转账,并受策略约束和人工审核控制。

可以做什么
通过 Yault 后端 API 查询地址的金库余额、多币种余额明细以及操作员/授权额度状态。向金库充值底层资产,并赎回金库份额。将金库额度从父账户转账至子账户。让支出操作经过策略引擎,按单笔与滚动预算限额、地址白名单和时间窗口约束,并将高风险操作升级至人工审核队列。
适用场景
当希望助手在 Yault 上执行或查看加密金库操作,同时让支出受策略与人工审核约束时使用。适合持有 Yault 金库、希望让代理在设定限额内查询余额或调动资金的终端用户。
运行要求
通过 npm 包 @yault/aesp 以 stdio 在本地运行,需要 Node.js 18 或更高版本。需要 Yault 账户及 API 密钥,通过环境变量 YAULT_API_KEY 提供;YAULT_API_URL 可选,用于设置后端基础地址。需要能访问 Yault 后端的网络。
安装前请注意
该服务器会调动真实资金:充值、赎回和转账会写入金库并产生实际支出。YAULT_API_KEY 与用户金库绑定并具有支出权限,应限制其范围并绑定策略。README 提示敏感操作应置于宽泛的代理密钥权限之外,策略违规时回退到人工升级处理。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Yault AESP,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

AESP - Agent Economic Sovereignty Protocol

Defining how AI agents operate economically under human sovereignty.

Website | npm

What Is AESP

AESP is a TypeScript SDK and MCP integration layer for agent payments under explicit human control. It is designed so that agents can execute economic actions while humans retain full economic sovereignty.

Core principles:

  • Policy-gated execution -- every spend action is bounded by configurable policy rules (per-tx limits, daily/weekly/monthly budgets, address allowlists, time windows).
  • Human override path -- risky actions are escalated to a review queue instead of being auto-approved.
  • Verifiable commitments -- execution context can be tied to EIP-712 signed intent, enabling on-chain settlement guarantees.
  • Practical integration -- MCP tools expose vault operations to AI agent frameworks; subpath exports let you import only what you need.

Install

bash
npm install @yault/aesp

Requires Node.js >= 18.

Quick Start

Add to Claude Desktop

Add the following to your Claude Desktop config (claude_desktop_config.json):

json
{  "mcpServers": {    "yault": {      "command": "npx",      "args": ["-y", "@yault/aesp"],      "env": {        "YAULT_API_KEY": "sk-yault-..."      }    }  }}

Add to Claude Code

bash
claude mcp add yault -- npx -y @yault/aesp

Then set the environment variable YAULT_API_KEY in your shell or .claude/settings.json.

Run standalone

bash
export YAULT_API_KEY="sk-yault-..."yault-mcp                  # if installed globallynpx @yault/aesp            # via npx

Get your API key

Go to yault.xyz to create an account and obtain your API key (sk-yault-*). The key is tied to your vault — each user manages their own key. Agent developers do not need a key unless they are also vault users; it is the end-user who configures their own key in the MCP client.

Use SDK modules

typescript
import { PolicyEngine } from '@yault/aesp/policy';import { getAllMCPTools } from '@yault/aesp/mcp';import { NegotiationStateMachine } from '@yault/aesp/negotiation';
const engine = new PolicyEngine(storageAdapter);await engine.load();
const tools = getAllMCPTools(); // 6 MCP tool definitions

Modules

AESP is organized into subpath exports so you can import only what you need:

SubpathDescription
@yault/aespUnified re-export of all modules
@yault/aesp/typesShared type definitions (AgentExecutionRequest, TransferPayload, ChainId, etc.)
@yault/aesp/policyPolicy engine with 8-check evaluation, budget tracking, and policy change classification
@yault/aesp/identityAgent identity derivation, certificate creation, and hierarchy management
@yault/aesp/negotiationOffer/counter-offer state machine with session management
@yault/aesp/commitmentEIP-712 structured commitment builder for dual-signed agreements
@yault/aesp/reviewHuman-in-the-loop review queue with freeze/unfreeze controls
@yault/aesp/mcpMCP tool definitions, argument validation, and server router
@yault/aesp/a2aAgent-card builder for cross-agent discovery (A2A protocol)
@yault/aesp/cryptoCryptographic helpers: signing, encryption, hashing, ZK proof bridge
@yault/aesp/privacyContext tagging, ephemeral address pools, and consolidation scheduling

MCP Tools

The stdio server exposes 6 backend-connected tools:

ToolMethod + EndpointPurpose
yault_check_balanceGET /api/vault/balance/:addressRead a wallet vault balance
yault_depositPOST /api/vault/depositDeposit underlying into vault
yault_redeemPOST /api/vault/redeemRedeem vault shares
yault_transferPOST /api/vault/transferTransfer vault allocation (parent to sub-account)
yault_check_authorizationGET /api/vault/agent-authorizationRead operator/allowance status
yault_get_balancesGET /api/vault/balances/:addressRead multi-balance breakdown

Backend Requirements

The MCP server is a thin API client. It expects a Yault backend providing:

  • GET /api/vault/balance/:address
  • GET /api/vault/balances/:address
  • GET /api/vault/agent-authorization
  • POST /api/vault/deposit -- { address, amount }
  • POST /api/vault/redeem -- { address, shares }
  • POST /api/vault/transfer -- { from_address, to_address, amount, currency? }

Authentication: Authorization: Bearer sk-yault-* via YAULT_API_KEY env variable.

Security Model

AESP is built around "bounded autonomy":

  • Agent API keys should be policy-bound before spend execution.
  • Spending controls should include per-tx and rolling limits (daily/weekly/monthly).
  • Destination constraints should be allowlist-driven where applicable.
  • Sensitive operations should stay outside broad agent key scopes.
  • Human escalation remains the fallback for policy violations.

For vulnerability reporting, see SECURITY.md.

Related Packages

PackageDescription
@yault/elizaos-plugin-aespElizaOS plugin wrapping AESP for agent frameworks

Development

Run tests:

bash
npm test

Build TypeScript:

bash
npm run build:ts

Build with WASM (requires acegf-wallet as a sibling repo, or set ACEGF_ROOT):

bash
npm run build:wasmnpm run build:ts

See CONTRIBUTING.md for the full development guide.

License

This project is licensed under the Apache License 2.0. See LICENSE for the full text.

来源:README.md,提交 73e8bc9

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v0.2.0最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分