SkillFoxx

ALGOPACK skills from the moexalgo team

algopack-skills

A set of skills for working with the Moscow Exchange's ALGOPACK data: access and auth, candles, order book, volumes and market alerts

  • 4 ★ on the repository
  • Last commit
  • MIT
SkillOfficial

Minimal access

Why this level

  • The skills only read market data, they do not execute trades
All reasons and checks
Russian stack

moexalgo/algopack-skillsAuthor:moexalgo

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/algopack-skills

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Minimal accessThe tool runs nothing and makes no network calls.

  • The skills only read market data, they do not execute trades

This is third-party code. Review the repository files before installing.

What it does

The repository gives an agent twelve skills covering ALGOPACK and ISS data from the Moscow Exchange: access and auth with 401 and 403 troubleshooting, candles and market data, the HI2 order book, futures open-interest FUTOI stats, MegaAlerts, and the production calendar. Each skill covers both a direct REST call with an Authorization Bearer header to apim.moex.com and working through the moexalgo Python library with a token in session.TOKEN. The skills are duplicated under two prefixes, algopack- and moexalgo-, with the same content.

Who it is for. For analysts and developers working with Moscow Exchange data through the ALGOPACK API or the moexalgo library.

Good fit when

  • You need help setting up ALGOPACK access and diagnosing auth errors
  • You need candles, the order book or futures open-interest stats through an agent
  • You need the Moscow Exchange trading production calendar

Not a fit when

  • You need a ready MCP server with tools, not a reference skill: separate projects like ru-moex-mcp cover that
  • You have no ALGOPACK token: some data is free, but full coverage needs the paid Promo subscription

Example request

Get the HI2 order book for Sberbank shares via ALGOPACK, and explain how to get a token if the request returns a 403

Limitations

These are reference skills with instructions and code examples, not a ready executable server: the agent makes the HTTP calls or invokes the moexalgo library itself, guided by the skill. The skills are duplicated under two identically-scoped name prefixes, which inflates the file count without adding functionality. The repository's own README is minimal; the substance lives in the SKILL.md files.

How to disable. Remove the relevant folders from your agent's skills directory.

FAQ

Do I need paid access?

Some data is available on the free Starter tier; full coverage and up-to-date data need the paid Promo subscription.

Do the skills make the exchange requests themselves?

No, a skill gives the agent instructions and curl or Python examples; the agent's own environment makes the actual requests.

How are the ALGOPACK skills different from working with the Moscow Exchange API yourself?

Twelve skills for ALGOPACK and Moscow Exchange ISS data: access and auth with diagnosis of 401 and 403 errors, candles and market data, the HI2 order book, open interest statistics and market alerts. They come from the moexalgo team.

Is paid ALGOPACK access needed and do the skills make requests themselves?

Some ALGOPACK data needs a subscription, see the exchange site for terms. The skills teach the agent how to call the API and parse answers, while requests run through your code and credentials. It connects to Claude Code.

Discussion

No questions or reviews yet.

All Moscow Exchange tools
Russian stack

An MCP server for MOEX AlgoPack: trade flow, order book, futures open interest and ready derived metrics in plain language

MCP serverExtended access1
Russian stack

An MCP server built on the official moexalgo library: 24 tools for candles, order book, trades and stats from MOEX ISS and ALGOPACK

MCP serverExtended access4
Russian stack

An MCP server for MOEX quotes and order books via ISS+ and ISS REST, plus a Telegram bot that picks the right tool itself via OpenAI tool calling

MCP serverExtended access
Russian stack

MCP server over the Moscow Exchange API: security search, prices, history, metrics, comparison with an index and a schedule mode, no keys needed

MCP serverExtended access
Russian stack

A client and MCP server for MOEX ISS on the Python standard library: quotes, candles, coupons, offers, OFZ yields and a skill for Claude

MCP serverExtended access

MOEX ISS MCP server (Go)

go_mcp_server_moex

Russian stack

A Go MCP server over the Moscow Exchange's public ISS information server: instruments, markets, boards and trading history with no key

MCP serverExtended access2

README in short

The README is short: it describes the repository as a set of ALGOPACK, ISS and ISS+ skills for agents and links to moexalgo.github.io. The real content lives in each skill's SKILL.md: the algopack-access skill, for example, explains the difference between free and paid access, shows a REST call with a Bearer header, and sets up session.TOKEN in the moexalgo library.

README badge

Original SKILL.md

---
name: algopack-access
description: ALGOPACK access, free and paid API keys, subscription, API key authorization, entitlement, and troubleshooting guidance for DataShop setup, bearer tokens, moexalgo .env session.TOKEN setup, direct REST headers, free or delayed access, 401, 403, 429, rate limits, and product boundaries.
---

# ALGOPACK Access

## Overview

Use this skill to help users get authenticated ALGOPACK access and diagnose subscription, key, entitlement, and rate-limit failures without exposing secrets.

## Core Workflow

1. Confirm whether the user is using direct REST/curl or the Python library.
2. Explain that Data MOEX/DataShop can provide free API-token access through Starter, while Promo is paid/subscribed access.
3. Tell users that entitlement, delay, and field coverage are account-plan dependent.
4. For direct REST, show Authorization: Bearer against https://apim.moex.com/iss.
5. For Python library workflows, store APIKEY in .env, call load_dotenv(), then set session.TOKEN.

Report a problem