What is MCP-Pionex CLAUDE.md?

A set of Claude Code instructions for developing and operating an MCP server for the Pionex cryptocurrency exchange. MCP is a way for an agent to call tools provided by another program.

It is for installing, running, testing, inspecting, and modifying the MCP-Pionex server, including its market, account, trading, bot, and investment tool groups.

It documents the project’s commands, structure, safety rules, tool patterns, and two-step commit process so changes follow the repository’s required conventions.

How alejandrorodm/MCP-Pionex configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to alejandrorodm/MCP-Pionex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/alejandrorodm/MCP-Pionex/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/alejandrorodm/MCP-Pionex

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/alejandrorodm/mcp-pionex/claude-md/github.svg)](https://agentmods.dev/instructions/alejandrorodm/mcp-pionex/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/alejandrorodm/mcp-pionex/claude-md"><img src="https://agentmods.dev/badge/instructions/alejandrorodm/mcp-pionex/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/alejandrorodm/mcp-pionex/claude-md"><img src="https://agentmods.dev/badge/instructions/alejandrorodm/mcp-pionex/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,185 This file is loaded in full into every session.

When invoked 3,185 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.03185	$0.03185
Opus 5.5	$0.01274	$0.01274
Sonnet 5.5	$0.00637	$0.00637
Haiku 4.5	$0.00318	$0.00318

Measured 2mo ago against content hash b59b534b2b85, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

MCP-Pionex CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — mcp-pionex

Servidor MCP para el exchange Pionex, construido sobre la librería pionex_py (dependencia desde PyPI; para desarrollar contra un checkout local en ../pionex_py, descomenta el override [tool.uv.sources] del pyproject). Expone mercado, análisis técnico, cuenta, trading spot, spot/futures grid bots y Dual Investment como herramientas MCP con una capa estricta anti-alucinación y anotaciones MCP en cada tool.

Repo: https://github.com/alejandrorodm/MCP-Pionex

Comandos

uv sync                          # instalar (crea .venv)
uv run mcp-pionex                # arrancar el servidor (stdio)
uv run --with pytest pytest tests/ -q   # tests offline (seguridad, anotaciones, idempotencia, TA)

Verificación rápida de registro de tools:

uv run python -c "
from mcp_pionex.server import mcp; import asyncio
print(len(asyncio.run(mcp.list_tools())), 'tools')"

Arquitectura

src/mcp_pionex/
├── server.py      # MCPServer (SDK mcp>=2.0), instructions anti-alucinación,
│                  # tools meta (get_server_status, get_safety_rules) y registro
│                  # de los grupos de tools
├── config.py      # Settings inmutables leídos del entorno; defaults conservadores
├── safety.py      # LA capa importante: vocabularios cerrados, verificación de
│                  # símbolos en vivo, two-phase commit, límites, envelopes,
│                  # errores verbatim, auditoría
├── client.py      # singletons perezosos de los clientes pionex_py
│                  # (con fix del doble-slash en base_url — ver Gotchas)
├── actions.py     # registro EXECUTORS: nombre de acción -> función ejecutora
├── ta.py          # análisis técnico puro (EMA/RSI/MACD/ATR/Bollinger, FVG,
│                  # order blocks, swings) — determinista, sin red, testeado
└── tools/
    ├── market.py   # público, sin credenciales
    ├── analysis.py # análisis técnico sobre klines vivas (todo computed:true)
    ├── account.py  # lectura, requiere credenciales
    ├── trading.py  # dos fases, requiere PIONEX_MCP_TRADING_ENABLED
    ├── bots.py     # dos fases, requiere PIONEX_MCP_BOTS_ENABLED
    └── earn.py     # dos fases, requiere PIONEX_MCP_EARN_ENABLED

Read the full file on GitHub · 225 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 225 lines · 3,185 tokens per session scan A b59b534b2b85

Subscribe to this mod's changes

MCP-Pionex CLAUDE.md is an instructions file published in the GitHub repository alejandrorodm/MCP-Pionex (0 stars, last pushed 2mo ago), licensed MIT. It adds 3,185 tokens to every session, about $0.0127 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

claude crypto-trading mcp model-context-protocol pionex

MCP-Pionex CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
MCP-Pionex CLAUDE.mdalejandrorodm/MCP-Pionex	Instructions file	0	2mo ago	MIT	A	3,185	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

MCP-Pionex: Instructions file for Claude Code