nvda-cpi-watch
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.
README
nvda-cpi-watch
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.
Quickstart
cd ~/repos/nvda-cpi-watch
cp .env.example .env
# Edit .env: FINNHUB_API_KEY=... (free key from https://finnhub.io/register)
# Dependencies sind im venv installiert. Falls nicht:
python3 -m venv venv && venv/bin/pip install -r requirements.txt
# 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-watch
Alternativ Standalone-Server testen:
venv/bin/python server.py < /dev/null # startet stdio-loop, EOF beendet
Tools
| 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) | TradingView (primary) + ForexFactory (fallback) + 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 |
Env
| 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/ |
Architektur
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 (primary consensus source)
├── forexfactory.py ← ForexFactory feed (fallback consensus source)
└── 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, Nowcast 3h.
Phase 1 = passiv
Aktuelle Phase: on-demand Daten-Server. Keine Alerts, keine Cron-Jobs, keine HA-Integration. Roadmap → vision.md.
Disclaimer
Daten-Server, keine Anlage- oder Trade-Beratung. Werte direkt aus BLS / Finnhub / Cleveland Fed; bei Drift Source pruefen.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.