fugle-mcp-server CLAUDE.md

fugle-mcp-server CLAUDE.md is an instructions file for coding agents from fugle-dev/fugle-mcp-server. It costs 595 tokens per session, scanned A, original, MIT.

Repository instructions for a Fugle MCP server that provides Taiwan stock-market data, trading operations, and company analysis through the Model Context Protocol.

In plain words
What is it for?
Use them when developing market-data, account, trading, or fundamental-analysis features for the server.
Why use it?
They describe the supported trading SDKs, shared architecture, development commands, and project structure so changes fit the existing design.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/fugle-dev/fugle-mcp-server/claude-md
Clone the repo
git clone --depth 1 https://github.com/fugle-dev/fugle-mcp-server

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.

agentmods badge for fugle-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fugle-dev/fugle-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/fugle-dev/fugle-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/fugle-dev/fugle-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/fugle-dev/fugle-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 595 This file is loaded in full into every session.
When invoked 595 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00595 $0.00595
Opus 5 $0.00298 $0.00298
Sonnet 5 $0.00119 $0.00119
Haiku 4.5 $0.00060 $0.00060

Measured 4d ago against content hash ec8bb8bceef5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fugle-mcp-server 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 4d 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 · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is a Fugle MCP (Model Context Protocol) Server for Taiwan stock market operations. The server supports two different trading platforms:

  • Taishin SDK (default)
  • Fubon Neo SDK

The server provides stock market data, trading functionality, and fundamental analysis tools through MCP protocol.

Architecture

The codebase follows a modular architecture with SDK abstraction:

  • src/index.ts - Main server entry point with environment validation
  • src/config.ts - Configuration management for SDK selection
  • src/shared/ - Common utilities and abstractions:
    • factory/ - SDK abstraction layer with unified interfaces
    • marketdata/ - Market data tools (intraday, historical, snapshots)
    • fundamental/ - Company analysis tools via Fugle API
  • src/taishin/ - Taishin SDK specific implementations
  • src/fubon/ - Fubon SDK specific implementations

Each SDK implementation provides:

  • account/ - Account management tools
  • trade/ - Trading operations
  • Shared market data tools through the factory pattern

Development Commands

# Build the project
npm run build

# Watch mode for development
npm run watch

# Test with MCP inspector
npm run inspector

# Run the server directly
node build/index.js

SDK Configuration

The server uses SDK_TYPE environment variable to switch between trading platforms:

  • taishin (default) - Uses Taishin SDK
  • fubon - Uses Fubon Neo SDK

Both SDKs are abstracted through the factory pattern in src/shared/factory/ to provide unified interfaces for market data operations.

Required Environment Variables

  • NATIONAL_ID - Taiwan National ID
  • ACCOUNT_PASS - Trading account password
  • CERT_PASS - Certificate password
  • CERT_PATH - Path to certificate file (defaults to /app/cert.p12)
  • SDK_TYPE - SDK selection (taishin or fubon)
  • ENABLE_ORDER - Enable trading functionality (default: false)
  • ACCOUNT - Specific account selection for multi-account users
  • FUBON_URL - Fubon SDK connection URL (optional, fubon only)
  • FUGLE_API_URL - Fugle API base URL override (optional, defaults to https://www.fugle.tw/api/v2)

Read the full file on GitHub · 73 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.

  1. 4d ago First seen · 73 lines · 595 tokens per session scan A ec8bb8bceef5

Subscribe to this mod's changes

fugle-mcp-server CLAUDE.md is an instructions file published in the GitHub repository fugle-dev/fugle-mcp-server (10 stars, last pushed 3mo ago), licensed MIT. It adds 595 tokens to every session, about $0.0030 per session on Opus 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.

Related

Other instructions, from other repositories

Convertible-Bond-Pricing-Research CLAUDE.md

Instructions for ericxuzhesheng/Convertible-Bond-Pricing-Research, covering claude.md — convertible bond pricing research, current published state and routine commands.

ericxuzhesheng/Convertible-Bond-Pricing-Research · 363 tokens

swiss-snb-mcp CLAUDE.md

Claude Code instructions for malkreide/swiss-snb-mcp, covering claude.md, teil 1 — konventionen (portfolio-weit), vor der arbeit, tests and wenn etwas rot ist.

malkreide/swiss-snb-mcp · 7,293 tokens

bullet-bots AGENTS.md

Instructions for bulletxyz/bullet-bots, covering bullet-bots, build & test, run the faucet curl printed by keygen, then, or (base58 from phantom/delegation export, or hex) and architecture — the harness, feeds, and actors.

bulletxyz/bullet-bots · 3,972 tokens

romaco-mcp AGENTS.md

AGENTS.md instructions for romaco-labs/romaco-mcp, covering purpose, read first, product boundaries, architecture invariants and development method.

romaco-labs/romaco-mcp · 679 tokens

financial-services-plugins-new CLAUDE.md

Claude Code instructions for yuping322/financial-services-plugins-new, covering financial services plugins, repository structure, plugin structure, key files and development workflow.

yuping322/financial-services-plugins-new · 286 tokens

zenmoney-mcp CLAUDE.md

Claude Code instructions for sakost/zenmoney-mcp, covering zenmoney mcp server — development guidelines, project overview, build & test, architecture and coding standards.

sakost/zenmoney-mcp · 383 tokens