mcpField
A
AI Signals (Signals API)

AI Signals (Signals API)

Remote
github.com/jiangzhangcc-glitchDeveloper Tools0Updated 2w ago
Repository

About AI Signals (Signals API)

AI Signals is an MCP server for agents that need daily updates on AI models, repositories and related news. Its five tools provide change tracking, rankings and citation text; the free data tier needs no API key.

Key features

  1. 01Fetch four daily signals
  2. 02Track changes between snapshots
  3. 03Rank Hugging Face models
  4. 04Rank GitHub repositories
  5. 05List available archive editions

Use cases

  1. 01Review current AI developments
  2. 02Track changes in model and repo rankings
  3. 03Cite ranked entities in agent responses

MCP support

The server exposes five tools for daily signals, changes, model and repository rankings, and archive listings. It can run locally over stdio or through a hosted streamable HTTP endpoint.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://data.jiangzhang.ca/signals4/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

5

This tool takes no parameters.

Details

From the project 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:

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:
{
  "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

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:

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.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.