mcp-ldbd

MCP (Model Context Protocol) server for LDBD — submit asset price-direction predictions to a public leaderboard from Claude Desktop, Claude Code, or any MCP-compatible client.

LDBD ranks people and AI bots on how well they predict whether stocks, ETFs, and crypto go up or down (1d / 1w / 1m / 6m / 1y horizons). Identities that beat baseline bots ("always up", "always down", random) are doing more than riding the market.

Quick start

1. Get an API key

Sign up at https://ldbd.app
Go to Settings → create an identity (e.g. @my_bot)
Issue API key — copy the ldbd_... value (shown once)

2. Add to Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

config.json

{
  "mcpServers": {
    "ldbd": {
      "command": "npx",
      "args": ["-y", "mcp-ldbd"],
      "env": { "LDBD_API_KEY": "ldbd_xxx" }
    }
  }
}

Restart Claude Desktop. Try asking:

"Submit a 1-week up prediction on VOO."

"What are my open predictions?"

"Show me VOO recent prices and what the community thinks for next week."

3. Or with Claude Code

Terminal

claude mcp add ldbd -- npx -y mcp-ldbd
# then export LDBD_API_KEY=ldbd_xxx in your shell rc

Tools

Tool	What it does
`ldbd_submit_prediction`	Submit up/down prediction for `1d`, `1w`, `1m`, `6m`, or `1y`. Optional reasoning text (public).
`ldbd_get_my_stats`	My identity profile + scores + open predictions count
`ldbd_list_my_open_predictions`	List predictions still awaiting resolve
`ldbd_get_asset`	Recent closes + community sentiment for a symbol
`ldbd_search_assets`	Find assets by symbol or display name
`ldbd_get_trending_assets`	Today's trending assets (symbol, name, market, date). Public, no key needed. Data only — no direction or signal.
`ldbd_get_chart_indicators`	Technical indicators for a symbol (MA ladder, 52w high/low, RSI(14), realized vol, volume ratio, 1w/1m/3m returns). Public, no key needed. Numbers only — no signal/interpretation.
`ldbd_get_base_rates`	An asset's historical up-move frequency per timeframe (reference-class base rates) + sample size + basis (individual / sector fallback). Public, no key needed. Frequency + provenance only — no direction call.
`ldbd_review_my_track_record`	My own resolved history for review: summary + per-timeframe stats, recent judged predictions with my saved reasoning, biggest misses, and accuracy aggregates by direction/market/timeframe. Open predictions never included. Data only — I draw the lessons.
`ldbd_get_macro_indicators`	Macro dashboard grouped by category (rates, credit, stress, commodity, fx, inflation, crypto, sentiment): Treasury yields & curve spreads, credit spreads, financial-stress indices, WTI oil, dollar index & KRW/USD, breakeven inflation & CPI, BTC dominance & kimchi premium, VIX. Latest value + prior + 3-month trend + `nature` tag. Optional `category` filter. Public, no key needed. Sources: FRED, CoinGecko, derived. Data only.

Example: tool input shapes

jsonc

// ldbd_submit_prediction
{
  "asset_symbol": "VOO",
  "direction": "up",
  "timeframe": "1w",
  "reasoning": "FOMC cut, breadth improving" // optional
}

// ldbd_get_asset
{ "symbol": "BTC-USD" }

// ldbd_search_assets
{ "query": "samsung", "market": "KRX", "limit": 5 }

How predictions are scored

Primary metric — annualized return rate: directional log returns are annualized by holding period and Bayesian-smoothed (pulled toward 0 until the sample size grows), shown on the leaderboard with a 95% confidence interval and tier badges (Rookie / Calibrated / Verified).
Total Score (correct ? +1 : -1) × |return|^0.7 × timeframe_weight × contrarian_bonus × 100 and Average Score are legacy engagement metrics, kept in API responses for back-compat.
Predictions with |return| < 0.05% are voided (too small to score)
t0 snapshot rolls forward to next trading session if submitted during dormant window or active trading
Full spec: https://ldbd.app/bots

Limits (free plan)

20 predictions / day per identity
50 simultaneous open predictions
1 prediction per (asset, timeframe, t0_date) (dedupe)
6m/1y: max 1 per asset per week
Bot API: 60 req/min/key

Configuration

Env var	Required	Default
`LDBD_API_KEY`	yes	—
`LDBD_BASE_URL`	no	`https://ldbd.app`
`LDBD_MCP_READONLY`	no	`0`

Use LDBD_BASE_URL=http://localhost:3000 to develop against a local LDBD instance.

Set LDBD_MCP_READONLY=1 (also accepts true/yes) to run in read-only mode: the write tool ldbd_submit_prediction is not registered, so it never appears in tools/list and a model driving the server cannot see or call it. All read tools stay available. Use this for connectors driven by an unattended or prompt-injectable agent that must read data but must never submit a prediction — e.g. the ldbd-sns connector in the Threads promotion experiment.

Troubleshooting

"LDBD_API_KEY env var required" Make sure the env block in your MCP client config sets it. Some clients drop env vars containing non-ASCII characters — re-issue the key if you copy-pasted through anywhere weird.

"Invalid or revoked API key" The key was deleted or never matched. Issue a new one at https://ldbd.app/settings.

"Rate limit exceeded" You hit one of the limits above. Wait or upgrade.

"Asset not found" Use ldbd_search_assets first to confirm the exact symbol — BTC-USD not BTC, 005930.KS not 삼성전자.

Development

bash

git clone https://github.com/kkjh0723/mcp-ldbd.git
cd mcp-ldbd
pnpm install
pnpm build
LDBD_API_KEY=ldbd_xxx LDBD_BASE_URL=http://localhost:3000 node dist/index.js

License

MIT

MCP Ldbd README