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)
Daily AI signals for agents: today's 4 signals, what changed, ranked models and repos
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://data.jiangzhang.ca/signals4/mcp在终端中运行这条命令
claude mcp add --transport http signals-api https://data.jiangzhang.ca/signals4/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"signals-api": {
"url": "https://data.jiangzhang.ca/signals4/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": {
"signals-api": {
"type": "http",
"url": "https://data.jiangzhang.ca/signals4/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://data.jiangzhang.ca/signals4/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。
工具名称和描述与服务器在 2026年11月8日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
daily_signalsToday's AI signals from Signals API: exactly 4 items, one from each core source (GitHub, Hugging Face, YouTube, Silicon Valley news), each linking to the original. Use when the user asks what's new in AI today.
what_changedWhat changed in the AI landscape since the previous snapshot: new entries, entities no longer seen, and rank movers. Use when the user asks what's moving, rising, or different lately.
top_modelsHugging Face models we track, with rank, rank change and 7-day momentum. Entries without a derivable number are marked 'not ranked' with a reason instead of a guessed value.
top_reposGitHub repositories we track, with rank, rank change and momentum. Use when the user asks which open-source AI projects are trending.
archive_daysList the archived daily editions (dates) available from the free digest. Use to find which dates can be cited.
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8日
注册名称已通过域名 api.jiangzhang.ca 验证(注册中心会核实域名所有权)
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
在 71 毫秒内响应(HTTP 200)
无需登录
已读取 5 个工具描述,未发现针对 AI 的隐藏指令
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 3 项适用的基础检查中通过了 3 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(1.0.0)于24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, Filesystem 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.
Filesystem MCP server for AI assistants.
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。
An MCP server that gives Claude / Cursor / any MCP client AI signals data: today's signals, what changed, and ranked AI models & repositories.
No API key needed for the free tier. Single file, Python standard library only — no pip install.
| Tool | What it returns |
|---|---|
daily_signals | Today's 4 signals — one from each core source (GitHub, Hugging Face, YouTube, Silicon Valley news), each linking to the original |
what_changed | Deltas since the previous snapshot: new entries, entities no longer seen, rank movers |
top_models | Hugging Face models with rank, rank movement and momentum, plus a ready-to-cite sentence |
top_repos | GitHub repositories, same shape |
archive_days | Which daily editions exist (for citing a specific date) |
Every ranked row carries a citation string, so an agent can cite the number instead of inventing one. Entities whose number cannot be derived are published as unranked with the reason — we would rather return "not ranked" than a made-up value.
There is also a hosted MCP endpoint, so no download and no local Python is needed — point any MCP client that speaks streamable HTTP at:
https://data.jiangzhang.ca/signals4/mcp
It is published in the official MCP Registry as ca.jiangzhang.api/signals-api-mcp and serves the same five tools as the single-file version. A quick check with curl:
curl -s -X POST https://data.jiangzhang.ca/signals4/mcp \
-H 'Content-Type: application/json' \ -H 'Accept: application/json, text/event-stream' \ -A 'my-agent/1.0' \ --data '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
(The User-Agent header matters here too — see the CDN note further down.)
mcp_server.py anywhere (e.g. ~/mcp/signals/mcp_server.py).{
"mcpServers": { "signals": { "command": "python3", "args": ["/absolute/path/to/mcp_server.py"] } } }
Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows). Restart the client and the five tools appear.
Requires Python 3.9+. No dependencies, no key, no signup.
echo '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"daily_signals","arguments":{}}}' \
| python3 mcp_server.py
This server reads the free endpoints, which cover one edition a day, 4 sources. If your agent needs more than that, there is a paid feed:
Attributed landing page (no plan chosen yet): → https://data.jiangzhang.ca/signals4/go?to=landing&src=mcp_github
There is also a one-time option (no subscription, no renewal): the compiled dataset bundle (single JSONL, indexed SQLite, tidy daily entity CSV), refreshed daily — https://buy.stripe.com/00w28r4W08qq8CcecHgw008
The free endpoints stay free — this repo will not start requiring a key.
The CDN in front of the API rejects the bare `Python-urllib/…` User-Agent and empty User-Agents with HTTP 403. requests, httpx, aiohttp, Go, node-fetch, axios, okhttp and curl are all fine — but if you write a plain-stdlib example and forget the header, you will see a 403 that looks like a broken API. This server always sends one. If you call the endpoints directly, set a User-Agent:
curl -H 'User-Agent: my-app/1.0' https://data.jiangzhang.ca/signals4/api/today.json
Signals are collected from public APIs and public feeds (GitHub trending, Hugging Face, YouTube channels, arXiv, LMSYS Arena, silicon-valley news, hardware/chips). Each item links to its original source; we do not rewrite it. Derived rankings and momentum are recomputed from our own daily snapshots by an automated audit that also reconciles the site pages with the JSON endpoints.
Data: CC BY 4.0 — free to read, quote, cite and use commercially with attribution to *Signals 4 (Signals API)*. Machine-readable mirror of the daily dataset: https://github.com/jiangzhangcc-glitch/ai-signals-daily
Provenance canary: signals4-canary-2f9d71c4a8 (kept for provenance if this data is mirrored).
https://data.jiangzhang.ca/signals4/api/today.json — today's 4 signals.../api/changes.json — deltas since the previous snapshot.../api/models.json · .../api/repos.json — ranked entities + citations.../api/archive.json — list of editionshttps://data.jiangzhang.ca/llms.txt — machine-readable site summaryThe server is a single file, stdio JSON-RPC, no framework. Read a request line, write a response line. initialize, tools/list, tools/call, ping are implemented; unknown methods return JSON-RPC -32601 rather than failing silently.
MIT licensed (the server code). The data keeps its own license above.