hbhqq9-bde-scoreBLOCK
🏆 Open-source multi-factor stock scoring API (0-100) | US/HK/A-Share 74 stocks | Zero signup | shields.io badges | GitHub Action | EU AI Act compliant
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
AI-Powered Multi-Market Stock Analysis via Model Context Protocol
[](https://modelcontextprotocol.io) [](https://registry.modelcontextprotocol.io) [](#compliance) [](LICENSE)
🤖 What is BDE ScoreTM?
BDE ScoreTM is an MCP (Model Context Protocol) Server that gives AI agents direct access to transparent, multi-factor quantitative stock scoring across US, HK, and A-share markets.
It is not a REST API wrapper — it is a native MCP server built with the MCP SDK that exposes structured tools, each returning explainable 7-factor scores.
73 stocks · 3 markets · 6 MCP tools · One comparable score per stock.
🔧 MCP Tools
BDE Score exposes 6 MCP tools that AI agents can call directly:
915c472a0c91OBSERVED · 2026-10-12Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add bde-score --env ALPACA_API_KEY=${ALPACA_API_KEY} --env ALPACA_API_SECRET=${ALPACA_API_SECRET} --env MCP_API_KEY=${MCP_API_KEY} --env REGISTRY_API_KEY=${REGISTRY_API_KEY} -- npx -y @claude-plugins/[email protected]{
"mcpServers": {
"bde-score": {
"command": "npx",
"args": [
"-y",
"@claude-plugins/[email protected]"
],
"env": {
"ALPACA_API_KEY": "${ALPACA_API_KEY}",
"ALPACA_API_SECRET": "${ALPACA_API_SECRET}",
"MCP_API_KEY": "${MCP_API_KEY}",
"REGISTRY_API_KEY": "${REGISTRY_API_KEY}"
}
}
}
}Exposed tools (5)
5 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
batch_score | read | Score multiple stocks in one call. Returns ranked results with composite scores and factor breakdowns for each stock. |
market_overview | read | Get overall market sentiment including average BDE score, breadth indicators, top/worst performers, and signal distribution. |
score_stock | read | Score a single stock using 7-factor composite model (VIX, Volume Profile, RSI, MACD, Bollinger, OBV, ATR). Returns composite score (0-100), signal classification, and factor breakdown. |
top_performers | read | Get top N performing stocks from a watchlist, sorted by composite score descending. |
worst_performers | read | Get worst N performing stocks from a watchlist, sorted by composite score ascending. |
Trust audit
BLOCKgrade F · trust 46/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (13 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (25)
blocked_hosts = ['localhost', 'metadata.google.internal', '169.254.169.254']
sudo apt-get update -qq
sudo apt-get install -y -qq wget unzip curl
sudo yum install -y -q wget unzip curl
sudo cp /tmp/futu-opend.service "$SERVICE_FILE"
sudo systemctl daemon-reload
alpaca_adapter.cpython-313.pyc
alpaca_client.cpython-313.pyc
bde_api.cpython-313.pyc
bde_stock_daily.cpython-313.pyc
broker_adapter.cpython-313.pyc
log_warn "启动: sudo systemctl start futu-opend"
log_warn "开机自启: sudo systemctl enable futu-opend"
SERVICE_FILE="/etc/systemd/system/futu-opend.service"
BDE_API_BASE = "http://127.0.0.1:8890"
API_BASE = "http://127.0.0.1:8890"
.tunnel_state.json
.feishu_msg_20260723_1151.txt
.feishu_msg_20260724_0551.txt
.balance_state.json
SYSTEM_DNA.md
- **验证**: `curl http://101.126.19.34:8890/` → 连接拒绝 ✅
[ | US/HK/A-Share 74 stocks | Zero signup | shields.io badges | GitHub Action | EU AI Act compliant
What tools does hbhqq9-bde-score expose?
5 in total: 5 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is hbhqq9-bde-score safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (46/100) and found 6 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does hbhqq9-bde-score need?
It reads ALPACA_API_KEY, ALPACA_API_SECRET, MCP_API_KEY and REGISTRY_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does hbhqq9-bde-score run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as @claude-plugins/bde-score at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (915c472a0c91), read on 2026-10-12. The repository is watched and re-audited when it changes.