MCP server for fetching NVDA earnings and US CPI data, including historical values, market forecasts, and an aggregated trade brief for the next CPI release.
SaferSkills independently audited nvda-cpi-watch (MCP Server) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
MCP-Server + Repo-Agent fuer NVDA-Earnings + US-CPI Daten. Liefert historische Werte, Markt-Forecasts (Finnhub), Live-Nowcasts (Cleveland Fed), und einen aggregierten Trade-Brief fuer den naechsten CPI-Release.
cd ~/repos/nvda-cpi-watch
./bootstrap.sh # idempotent: venv + requirements + .env aus Vorlage
# Edit .env: FINNHUB_API_KEY=... (free key from https://finnhub.io/register)
# Agent spawnen (Repo-MCP wird automatisch geladen via .mcp.json):
tmux new-session -d -s nvda-cpi-watch "cd ~/repos/nvda-cpi-watch && claude --mcp-config .mcp.json"
tmux attach -t nvda-cpi-watchAlternativ Standalone-Server testen:
venv/bin/python server.py < /dev/null # startet stdio-loop, EOF beendet| Tool | Zweck | Quelle |
|---|---|---|
cpi_latest | Letzter Headline + Core CPI, MoM/YoY | BLS API v2 |
cpi_history(months=N) | Reihe der letzten N Monate | BLS API v2 |
cpi_next_release | Naechster Release-Termin | BLS Schedule (hardcoded) |
cpi_consensus | Markt-Konsens: Headline YoY/MoM, Core MoM (direkt) + Core YoY (derived) | Median aus TradingView + ForexFactory + Investing.com, dazu BLS |
cpi_forecast | DEPRECATED. Finnhub-Index, kein YoY. | Finnhub |
cpi_nowcast | Cleveland Fed Live-Modell | clevelandfed.org (HTML-scrape) |
cpi_trade_brief | Aggregat: Konsens (incl. derived Core YoY) + Nowcast + Previous + Spreads | alle |
nvda_earnings_history(quarters=N) | Letzte N Quartale | Finnhub |
nvda_earnings_next | Naechster Earnings-Termin | Finnhub |
| Var | Notwendig | Quelle |
|---|---|---|
FINNHUB_API_KEY | Ja, fuer Forecast + Earnings | https://finnhub.io/register |
BLS_API_KEY | Nein (optional, hoehere Limits) | https://data.bls.gov/registrationEngine/ |
server.py ← MCP stdio, Tool-Registry, Dispatch, derivations
├── bls.py ← BLS API client + CPI Release Schedule
├── finnhub.py ← Finnhub client (Earnings + Economic Calendar)
├── clevelandfed.py ← HTML scraper fuer Inflation Nowcasting
├── tradingview.py ← TradingView calendar (consensus source, median)
├── forexfactory.py ← ForexFactory feed (consensus source, median)
├── investing.py ← Investing.com event-page scraper (consensus source, median)
└── cache.py ← File-Cache (TTL je Tool)Core YoY Derivation: Free APIs publizieren keinen direkten Core-CPI-YoY-Konsens (nur Core MoM). Wir berechnen es deterministisch: core_yoy_forecast = (latest_core_idx × (1 + core_mom_forecast/100)) / year_ago_core_idx - 1 mit latest_core_idx und year_ago_core_idx aus BLS. Source-Transparenz im _derivation-Feld des Briefs.
Cache-Files unter cache/*.json (gitignored). TTLs: BLS 6h, Finnhub Earnings 1h, Forecast 30min, Konsens 15min, Nowcast 3h.
Aktuelle Phase: on-demand Daten-Server. Keine Alerts, keine Cron-Jobs, keine HA-Integration. Roadmap → docs/vision.md, Stand → docs/STATUS.md.
Daten-Server, keine Anlage- oder Trade-Beratung. Werte direkt aus BLS / Finnhub / Cleveland Fed; bei Drift Source pruefen.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.