yieldsentinel

io.github.agentsherpa由 GitHub 账号 agentsherpa 发布v1.0.0更新于 Nov 2, 2026

Policy check on a described yield position. Complement to yieldhunter. Research only.

已验证Streamable HTTP可网页运行金融AI 与机器学习

概览

AI 生成的概览

远程 MCP 服务，按研究策略评估所描述的稳定币收益仓位并给出结论；仅供研究，不执行交易。

可以做什么
  • 检查服务健康与能力，包括状态、schema 版本、策略版本、功能开关和可用工具列表
  • 按你提供的策略规则或预设，评估所描述的稳定币收益仓位并给出结论
  • 可传入配套收益排行服务中的池子标识，把检查对应到具体机会
适用场景
当助手在研究稳定币收益机会，并需要在据此行动前对某个已描述的仓位做基于策略的复核时使用。它是研究辅助工具，不是执行或退出工具。
运行要求
远程 Streamable HTTP 端点；未声明需要安装包、账号、API 密钥或环境变量。需要能访问该托管服务的网络，并且必须提供策略（自有规则或预设）才能得到有意义的结论。
安装前请注意
结论仅供研究，不构成存入或退出指令；未提供策略时结果只会是 review 或 unknown，绝不会是 ok。该服务只是私有代理的公开入口，README 说明它与配套排行服务之间不会自动同步。它声明不托管资金、不执行交易，但收益或 DeFi 相关输出仍应视为未经核实的研究信息。

安装

在 SourceWeft 中

  1. 打开 控制台中的 yieldsentinel，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。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.agentsherpa%2Fyieldsentinel/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "yieldsentinel": {
      "type": "http",
      "url": "https://yieldsentinel-agent-production.up.railway.app/mcp"
    }
  }
}

README

yieldsentinel-connect

Public front door for yieldsentinel.eth.

Policy check on one described position. Research only. Not a deposit or exit order. ERC-8004 on Base: 63771.

The full agent stays in a private repo. This repo only points at the live service.

Sibling

Ranks first via yieldhunter-connect / yieldhunter.eth (Base 61006, not RNWY Ethereum 12099).

No auto-sync between the two.

Live URLs

Connect snippet

See connect.json. Paste that block into an MCP client that accepts a remote URL.

Agent Plugin (Cursor / Grok marketplace)

This repo is also an Agent Plugins package:

  • plugin.json — manifest
  • mcp.json — remote Streamable HTTP MCP
  • LICENSE — MIT

Marketplace note (approval risk): this is DeFi / stablecoin research policy checking for agents. It never custodies funds, never executes, never auto-exits. Curated marketplaces may still reject or delay listings that touch yield/DeFi topics. Research only — not a deposit or exit order.

One-liner: Risk-adjusted ranks, then a policy check. Research only.

Files

  • connect.json — MCP connect snippet
  • agent-card.json — thin pointer (not the live tool list)
  • plugin.json — Agent Plugins manifest
  • mcp.json — Agent Plugins MCP config
  • LICENSE — MIT
  • README.md — this file

来源：README.md，提交 91a844b

工具

2

health

Health

Liveness and capability check for yieldsentinel (yieldsentinel.eth). Returns service status, schemaVersion, policyVersion, feature flags, and the list of available tools. May refresh research vintage via a yieldhunter health ping; a verdict still requires check_position. YH healthy ≠ YS ok. Use this first to verify connectivity, then call check_position with policyPreset treasury-conservative | balanced-research | rwa-selective (or explicit thresholds). Research estimates only — non-custodial; never holds keys or executes transactions. Example input: {}

无需输入参数。

check_position

Check position (research policy)

Evaluate a described stablecoin yield position against a research policy (pull). Always pass your policy rules (or a preset). Without a policy, no meaningful check is possible — the verdict will be review/unknown, never ok. Pass poolId from yieldhunter list_yields opportunities[].id (also accepted as opportunityId or id). That id is one market. Required for a real check: policyPreset (treasury-conservative | balanced-research | rwa-selective) and/or minScore / maxRewardShare / excludeCategories / maxExitRisk / requireCurated. Presets: treasury-conservative | balanced-research | rwa-selective. rwa-selective does not exclude RWA but is not a free pass (YS policy allowlist + higher bar). requireCurated uses the Yieldsentinel policy allowlist (curated.json), not yieldhunter scoring priors. Scoring ≠ policy approval. Fetches live yieldhunter research (score, APY, TVL, category, rewardShare, exitRisk) and curated flags, then returns a PolicyVerdict plus A2H (summary, suggestedNextSteps, legend). Incomplete or missing data is review/unknown — never a silent ok. A verdict is not an exit signal or execution order. Research only — never holds keys. Example: { "poolId": "43641cf5-a92e-416b-bce9-27113d3c0db6", "policyPreset": "treasury-conservative", "notionalUsd": 10000 }

输入参数idassetchainpoolIdminScoreminNetApyminTvlUsdhorizonDaysmaxExitRisknotionalUsdpolicyPresetprotocolSlug另有 6 个

版本历史

1
  1. v1.0.0最新Sep 16, 2026

评分

已满足适用检查项的 100%

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 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分