Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Discover DeFi yield opportunities and manage Zyfai positions with self-custodial AI agents.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
https://mcp.zyf.ai/mcp在终端中运行这条命令
claude mcp add --transport http zyfai https://mcp.zyf.ai/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"zyfai": {
"url": "https://mcp.zyf.ai/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"zyfai": {
"type": "http",
"url": "https://mcp.zyf.ai/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
https://mcp.zyf.ai/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 ondefy 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(1.1.0)于34天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Aiterm MCP
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Persistent terminals and one launcher for Claude, Codex, Grok, Cursor, and Antigravity harnesses.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Use Zyfai from Claude, Grok and Grok Bot, Cursor, Claude Code, compatible custom agents, and a limited ChatGPT preview.
This public Model Context Protocol server exposes Zyfai's yield discovery and personalized DeFi agent through natural-language tools. Discover opportunities, compare strategies, inspect positions, review earnings, and prepare supported account actions without building a separate integration.
Hosted MCP endpoint:
https://mcp.zyf.ai/mcp
You do not need to clone or run this repository to use the hosted server.
The server is built on @zyfai/sdk and uses remote Streamable HTTP transport.
| Client | How to connect | Positioning |
|---|---|---|
| Claude | Add a custom connector using the hosted endpoint | Recommended conversational experience |
| Cursor | Add the JSON configuration below | Developer workflows |
| Claude Code | Run the command below | Terminal and coding-agent workflows |
| Grok and Grok Bot | Add a Custom connector at grok.com/connectors | Longer-running and repeat agent workflows |
| ChatGPT | Limited private preview; currently desktop-only | Public distribution not yet available |
| Other clients | Configure the hosted URL as a remote Streamable HTTP server | Custom agents and integrations |
For current screenshots, authentication behaviour, mobile/desktop availability, and troubleshooting, see Use Zyfai with AI.
{
"mcpServers": { "zyfai": { "url": "https://mcp.zyf.ai/mcp", "transport": "http" } } }
Run this outside an active Claude Code session:
claude mcp add --transport http zyfai https://mcp.zyf.ai/mcp
In Claude, open Customize → Connectors, add a custom connector named Zyfai, and set the remote MCP URL to https://mcp.zyf.ai/mcp. Select Continue, then sign in. Full click-path: Use Zyfai with AI.
Open grok.com/connectors, select New Connector → Custom, and enter the hosted endpoint. In Grok Bot, attach the installed Zyfai connector with @ when needed.
Grok Bot is the better fit for longer-running or repeat workflows. Grok web also supports the connector for ad hoc conversations, although tool-heavy requests can take longer to complete.
Start with public opportunity discovery:
Using Zyfai, show me conservative USDC opportunities on Base. Compare APY, TVL, protocol, and risk.
Then compare strategies:
Now compare those with the aggressive strategy and explain the additional risk rather than recommending purely by APY.
After authentication:
Show my current Zyfai positions and earnings. Do not prepare any transaction.
For a controlled action flow:
Help me prepare a 1 USDC deposit on Base using the conservative strategy. Explain each step and ask before anything requiring a wallet signature.
Zyfai separates general discovery from personal account access.
OAuth challenges are returned through standard HTTP 401 and WWW-Authenticate responses so compatible clients can begin the authentication flow.
| Audience | Start here |
|---|---|
| AI assistant users | Use Zyfai with AI |
| Application and agent developers | Zyfai SDK quickstart |
| SDK-based autonomous agents | Agent quickstart |
| MCP server contributors | AGENTS.md |
Requirements: Node.js 18+ and pnpm.
git clone https://github.com/ondefy/zyfai-mcp-server
cd zyfai-mcp-server cp .env.example .env pnpm install pnpm run check pnpm start
Local endpoints:
http://localhost:3005/mcphttp://localhost:3005/healthSet ZYFAI_API_KEY in .env for live Zyfai API calls. See .env.example for authentication, backend, CORS, write-tool, and signing configuration.
For workspace-linked SDK development, local OAuth, integration testing, and the full repository architecture, read AGENTS.md.
pnpm run check
This runs TypeScript validation, the production build, and unit tests. Integration suites are opt-in; see AGENTS.md.
This public server is separate from zyf-knowledge-mcp, Zyfai's internal code and documentation search service.
ISC