๐ 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
bde-score is an early-stage Python project in the AI payments / x402 ecosystem, focused on a-shares, ai-agents, blockchain, eu-ai-act. It currently has 5 GitHub stars and 0 forks, and sits alongside related tools like x402-payments-mcp, Agent402, magpie-x402, AgentFund, 402-crypto, AgenticDeFi-Trainer.
AI-Powered Multi-Market Stock Analysis via Model Context Protocol
BDE Scoreโข 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 โ it is a native MCP server built with the MCP SDK that exposes structured tools, each returning explainable 7-factor scores.
73 stocks ยท 3 markets ยท 6 MCP tools ยท One comparable score per stock.
BDE Score exposes 6 MCP tools that AI agents can call directly:
| Tool | Description |
|---|---|
get_bde_score |
Get BDE composite scores (0-100) for all stocks in a market (US/HK/CN/ALL). Returns 7-factor breakdown: VIX, Volume Profile, Momentum, Mean Reversion, Volume, Volatility, Trend. |
get_stock_analysis |
Detailed single-stock analysis with factor-by-factor breakdown, signal classification (Bullish/Neutral/Bearish), and price context. |
get_multi_market_comparison |
Compare the same company's scores across US, HK, and CN markets (e.g., compare BYD on NASDAQ vs HK vs Shenzhen). |
get_stock_screener |
Screen stocks by minimum BDE score threshold. Returns ranked list of stocks meeting criteria. |
get_sector_analysis |
Sector-level aggregation: average scores per sector, sector rankings, and relative strength. |
get_esg_analysis |
ESG (Environmental, Social, Governance) analysis per stock with compliance metadata. |
Tool: get_bde_score
Input: { "market": "US" }
Output:
{
"AAPL": { "bde_score": 72, "signal": "BULLISH", "factors": { "momentum": 85, "volatility": 68, ... } },
"NVDA": { "bde_score": 81, "signal": "BULLISH", "factors": { ... } }
}
Add to claude_desktop_config.json:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"bde-score": {
"url": "https://enjoying-wide-boat-stan.trycloudflare.com/mcp",
"headers": {
"X-API-Key": "your-api-key-here"
}
}
}
}
Restart Claude Desktop. BDE Score tools will appear in the tool list.
Add to .cursor/mcp.json in your project:
{
"mcpServers": {
"bde-score": {
"url": "https://enjoying-wide-boat-stan.trycloudflare.com/mcp",
"headers": {
"X-API-Key": "your-api-key-here"
}
}
}
}
BDE Score uses the Streamable HTTP transport (MCP protocol). Connect from any MCP-compatible client:
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client
async with streamablehttp_client("https://enjoying-wide-boat-stan.trycloudflare.com/mcp") as (read, write, _):
async with ClientSession(read, write) as session:
await session.initialize()
tools = await session.list_tools()
result = await session.call_tool("get_bde_score", {"market": "US"})
print(result)
For local development without network:
pip install mcp httpx
cd mcp/
python mcp_http_server.py
Then configure your MCP client to use stdio:
{
"mcpServers": {
"bde-score": {
"command": "python",
"args": ["mcp/mcp_http_server.py"]
}
}
}
| Tier | Price | Access |
|---|---|---|
| Free | $0 | 3 MCP tool calls/day |
| Premium | $29/mo | Unlimited MCP calls + 365-day history |
| Institutional | $199/mo | Custom universe + compliance reports + SLA |
Payment: USDC on Base chain (x402 payment protocol supported)
AAPL, MSFT, GOOG, AMZN, META, NVDA, AMD, AVGO, ARM, INTC, V, MA, JNJ, UNH, LLY, PFE, PG, KO, WMT, MCD, TSLA, NFLX, BABA, SPY, QQQ
00700 (Tencent), 09988 (Alibaba), 09888 (Baidu), 03690 (Meituan), 01024 (Kuaishou), 01810 (Xiaomi), 09618 (JD), 09999 (NetEase), 02015 (Li Auto), 09868 (XPeng), 01211 (BYD), 09863 (Leapmotor), 02318 (Ping An), 01398 (ICBC), 00939 (CCB), 03988 (BOC), 02628 (China Life), 02899 (Zijin Mining), 00883 (CNOOC), 00857 (PetroChina), 01088 (China Shenhua), 00941 (China Mobile), 00728 (China Telecom), 00762 (China Unicom), 01833 (Ping An Good Doctor), 02269 (WuXi Biologics)
SH600519 (Moutai), SZ000858 (Wuliangye), SZ000568 (Luzhou Laojiao), SH600887 (Yili), SZ002714 (Muyuan), SH601318 (Ping An), SH600036 (CMB), SH601398 (ICBC), SH601288 (ABC), SZ300750 (CATL), SH601012 (LONGi), SZ002594 (BYD-A), SH600900 (Yangtze Power), SH688981 (SMIC), SZ002475 (Luxshare), SZ002230 (iFlytek), SH603501 (Will Semi), SH601899 (Zijin-A), SH601088 (China Shenhua), SH600585 (Conch Cement), SZ000333 (Midea), SH600690 (Haier), SZ000651 (Gree)
BDE Scoreโข is compliance-first by design. When Art.50 takes effect on August 2, 2026, our MCP server is already ready:
.well-known/ai-trust.txt and receipt responses78% of AI system operators have NOT taken Art.50 compliance measures yet (April 2026 data). BDE Scoreโข closes this gap โ the only open-source MCP server with built-in regulatory compliance.
BDE Score implements standard agent discovery protocols:
| Endpoint | URL |
|---|---|
| MCP Server | https://enjoying-wide-boat-stan.trycloudflare.com/mcp |
.well-known/mcp.json |
https://hbhqq9.github.io/bde-score/.well-known/mcp.json |
.well-known/agent.json |
https://hbhqq9.github.io/bde-score/.well-known/agent.json |
.well-known/agent-card.json |
https://hbhqq9.github.io/bde-score/.well-known/agent-card.json |
.well-known/security.txt |
https://hbhqq9.github.io/bde-score/.well-known/security.txt |
.well-known/ai-trust.txt |
https://hbhqq9.github.io/bde-score/.well-known/ai-trust.txt |
| Dashboard | https://hbhqq9.github.io/bde-score/ |
mcp package (FastMCP) + @modelcontextprotocol/sdk (TypeScript)For Claude Code users who prefer a local, self-contained MCP plugin:
cd claude-code-plugin/plugins/mcp/bde-score
npm install
npm start
This runs the BDE scoring engine locally via stdio transport โ no network required, no API keys needed for the local plugin.
Local tools:
| Tool | Description |
|---|---|
score_stock |
Score a single stock using 7-factor composite model |
batch_score |
Score multiple stocks in one call with ranked results |
top_performers |
Get top N performing stocks from a watchlist |
worst_performers |
Get worst N performing stocks from a watchlist |
market_overview |
Get overall market sentiment including VIX level |
BDE Scoreโข is a technical analysis tool, NOT financial advice. All investment decisions should be made independently. Past performance does not guarantee future results. This service does not provide investment suitability assessments.
Dual License โ AGPL-3.0 / Commercial
BDE Scoreโข โ MCP-Native. Multi-Market. Compliance-Ready.
Dashboard ยท
GitHub ยท
MCP Registry
Give AI agents a wallet โ x402 payment tools over Model Context Protocol.
500+ pay-per-call web tools + skill packs for AI agents โ every one tested, priced, and settled on-chain. Paid in USDC over x402 on 8 chains, or free via proof-of-work on the pure-CPU tools. Self-hostable, MCP-native, deterministic. Plus the open x402 index (Find / Route / Leaderboard).
Collateral that can still sell itself โ Magpie's x402 agent API: borrow SOL programmatically on Solana.
Fundraising infrastructure for AI agents on Solana โ x402 payments, milestone escrow, on-chain reputation. REST + WebSocket + MCP + ACP.
Curated BTC market data for AI agents via MCP. x402 autonomous payment on Arbitrum. 36 products, 7 sources, multi-timeframe analysis, reliability scoring. https://402-crypto.com
Autonomous AI Agent Swarm framework with x402 self-executing wallets. Empowers LLM-driven agents to trade, bridge, and manage crypto treasuries without human intervention. The ultimate Agentic DeFi toolkit for 2026.
The agent-native LLM router for autonomous agents. 55+ models (8 free), <1ms local routing, USDC payments on Base & Solana via x402.
The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
Self-healing infrastructure for AI agent payments. 90.3% auto-recovery.
The AI agent with a wallet โ spends USDC autonomously to get real work done. Apache-2.0, TypeScript.
Daydreams is a set of tools for building agents for commerce
Live data for AI agents โ search, research, markets, crypto, X/Twitter. Pay-per-call via x402 micropayments.