AI Signals (Signals API)

ca.jiangzhang.api由 api.jiangzhang.ca 發布v1.0.0更新於 Oct 25, 2026

Daily AI signals for agents: today's 4 signals, what changed, ranked models and repos

發布方自己的服務:SIGNALS Loyalty Agent Platform

已驗證Streamable HTTP可網頁執行資料與分析AI 與機器學習

概覽

AI 產生的概覽

一個遠端 MCP 伺服器,為助理提供每日 AI 訊號、變化摘要,以及附引用的 Hugging Face 模型和 GitHub 儲存庫排名。

可以做什麼
取得當天四則 AI 訊號,分別來自 GitHub、Hugging Face、YouTube 和矽谷新聞,附原始連結,每列帶引用字串。對照上一份快照,查看新增項目、消失的實體和排名變動。列出追蹤的 Hugging Face 模型和 GitHub 儲存庫,含排名、排名變化與動能。列出已封存的每日版本,方便引用特定日期。
適用情境
適合在使用者詢問今天 AI 領域有什麼新動態、哪些開源 AI 專案或模型正在竄紅、或相較上次快照有何變化時使用,讓回答基於可引用的數字而非猜測。
執行需求
遠端 streamable HTTP 端點;免費層無需 API 金鑰、註冊或本機執行環境。README 另述一個單檔 Python 3.9+ 版本,無相依套件。需要網路存取;直接呼叫時須設定 User-Agent 標頭,因為 CDN 會拒絕空白或裸 Python-urllib 的代理。
安裝前請注意
免費層每天僅一個版本、四個來源;更廣的來源、更高更新頻率和完整歷史以付費訂閱或一次性資料集購買提供,留意可能出現的付費引導。此伺服器只讀取資料,不寫入或刪除任何內容。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 AI Signals (Signals API),將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/ca.jiangzhang.api%2Fsignals-api-mcp/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "ai-signals-signals-api": {
      "type": "http",
      "url": "https://data.jiangzhang.ca/signals4/mcp"
    }
  }
}

README

Signals API — MCP server

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.

What it gives an agent

ToolWhat it returns
daily_signalsToday's 4 signals — one from each core source (GitHub, Hugging Face, YouTube, Silicon Valley news), each linking to the original
what_changedDeltas since the previous snapshot: new entries, entities no longer seen, rank movers
top_modelsHugging Face models with rank, rank movement and momentum, plus a ready-to-cite sentence
top_reposGitHub repositories, same shape
archive_daysWhich 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.

Use it without installing anything (hosted endpoint)

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:

bash
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.)

Install

  1. Download mcp_server.py anywhere (e.g. ~/mcp/signals/mcp_server.py).
  2. Add it to your MCP client config:
json
{  "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.

Try it without an MCP client

bash
echo '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"daily_signals","arguments":{}}}' \  | python3 mcp_server.py

Free tier vs the paid feed

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:

  • 8 sources instead of 4 (adds arXiv, LMSYS Arena, hot-topic aggregation, hardware/chips)

  • 4 updates a day instead of one daily edition (email / WebPush / API)

  • full history and machine-readable archives, with a stable API key

  • BASIC — CA$9.90/month — Core 4 sources, 18 boards × Top 3 per board, one morning push email (08:00 Beijing). Subscribe: https://data.jiangzhang.ca/signals4/buy?plan=basic

  • PLUS — CA$29.90/month — All 8 sources, choose push method and times (4×/day), Top 3 per board, plus API access to today's signals and stats. Subscribe: https://data.jiangzhang.ca/signals4/buy?plan=plus

  • BUSINESS — CA$129.90/month — PLUS, plus your own content and quantity per board (3–10), searchable history and full export. Subscribe: https://data.jiangzhang.ca/signals4/buy?plan=business

Attributed landing page (no plan chosen yet): → https://data.jiangzhang.ca/signals4/go?to=landing&src=mcp_github

Pay once instead of subscribing

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.

A trap worth knowing (we hit it ourselves)

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:

bash
curl -H 'User-Agent: my-app/1.0' https://data.jiangzhang.ca/signals4/api/today.json

Data sources and license

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).

Endpoints behind the tools

  • 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 editions
  • https://data.jiangzhang.ca/llms.txt — machine-readable site summary

Development

The 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.

來源:README.md,提交 97b3655

工具

5

daily_signals

Today'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.

無需輸入參數。

what_changed

What 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.

無需輸入參數。

top_models

Hugging 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.

輸入參數limit

top_repos

GitHub repositories we track, with rank, rank change and momentum. Use when the user asks which open-source AI projects are trending.

輸入參數limit

archive_days

List the archived daily editions (dates) available from the free digest. Use to find which dates can be cited.

無需輸入參數。

版本歷史

1
  1. v1.0.0最新Oct 15, 2026

評分

已滿足適用檢查項的 90%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

    請在儲存庫或註冊中心條目中宣告授權條款。

其他 Signals 整合