mcpField
M
moexalgo-mega-alerts

moexalgo-mega-alerts

github.com/moexalgoData & databases440 installsUpdated 19w ago
Repository

About moexalgo-mega-alerts

A skill for using Mega Alerts through the `moexalgo` Python package and analyzing results as DataFrames. It covers market-wide and instrument-specific queries, pagination, and historical context without framing alerts as forecasts or recommendations.

Key features

  1. 01Query via `Market` or `Ticker`
  2. 02Analyze results as DataFrames
  3. 03Group alerts by type, ticker, and time
  4. 04Paginate with library `offset`
  5. 05Parse historical `reference` context

Use cases

  1. 01Analyze market-wide alerts in Python
  2. 02Review alerts for a single instrument

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/moexalgo/algopack-skills --skill moexalgo-mega-alerts

After installing, type/moexalgo-mega-alertsin Claude Code to confirm it loaded.

Bundled filesreferences/mega-alerts.md

Details

From the project README

MOEXAlgo Mega Alerts

Overview

Use this skill when the user wants Mega Alerts through the moexalgo Python package and DataFrame analysis.

Access note: Promo includes Mega Alerts. Стартовый / Starter free-token availability is planned at T - 1 day; verify current access before promising it.

Quick Start

python -m pip install "moexalgo[dataframe]" python-dotenv

import json
import os
from dotenv import load_dotenv
from moexalgo import session, Market, Ticker

load_dotenv()
session.TOKEN = os.environ["APIKEY"]

eq = Market("EQ")
alerts = eq.alerts(date="2025-01-10")

sber = Ticker("SBER")
sber_alerts = sber.alerts(start="2025-01-01", end="2025-03-30")
parsed = sber_alerts["reference"].dropna().map(json.loads)

Core Workflow

  1. Use Market("EQ"|"FO").alerts(date=...) for market-wide alerts.
  2. Use Ticker(...).alerts(start=..., end=...) for one instrument.
  3. Group by alert_type, ticker, and date/time.
  4. Use library offset for pagination where supported; do not pass raw REST start to library methods.
  5. Parse reference only when historical post-alert context is needed.
  6. Avoid forecast language and recommendations.

References

Read references/mega-alerts.md for signatures, alert types, fields, reference parsing, and DataFrame examples.

Boundary

For raw endpoint URLs, curl, JSON/CSV, or no-Python workflows, use the direct Mega Alerts skill instead.

Comments

Markdown supported