bitcoin-risk-brief
LocalAbout bitcoin-risk-brief
Bitcoin Risk Brief provides a daily Bitcoin risk metric, freshness status, and hypothetical price scenarios for people monitoring BTC/USD data. Its versioned method and validation information make the analytics reproducible; it is research context, not advice.
Key features
- 01Daily Bitcoin risk metric and state
- 02Two-year risk history chart
- 03Completed-candle HLC3 price context
- 04Scenario price ladder by risk level
- 05Freshness and readiness checks
- 06Daily brief in seven languages
Use cases
- 01Check whether the latest risk data passed freshness checks
- 02Review Bitcoin risk history and current state
- 03Explore hypothetical prices associated with risk levels
- 04Provide agents with dated analytics and validation context
MCP support
Exposes read-only analytics endpoints for AI agents and API clients. Agent guidance requires checking `/api/readiness` first and tying values to their dates and freshness state.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @akarazhev/bitcoin-risk-brief-mcpBRB_API_BASE_URLBase URL of the Bitcoin Risk Brief API. Defaults to the public instance at https://bitcoinriskbrief.minihub.app.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
5Saved tool list · updated 2w ago
This tool takes no parameters.
Details
From the project READMEBitcoin Risk Brief
Bitcoin Risk Brief is a free, open-source product that turns canonical daily BTC/USD data into a transparent risk score, freshness state, and scenario price ladder. It is free permanently: no paid tier, no accounts, no SLA. The owned source code, documentation, and configuration are Apache-2.0; bundled third-party BTC/USD market data is not.

First viewport captured on 2026-08-09; the values shown are a point-in-time example.
Live product: bitcoinriskbrief.minihub.app
Check readiness before using any current value:
curl --fail --silent --show-error https://bitcoinriskbrief.minihub.app/api/readiness
Response captured on 2026-08-09:
{
"status": "ready",
"checks": {
"risk_data_available": true,
"validation_available": true,
"risk_range_ok": true,
"validation_has_rows": true,
"latest_matches_validation_end": true,
"source_is_canonical": true,
"data_fresh": true
},
"data": {
"latest_date": "2026-08-08",
"covered_end": "2026-08-08",
"data_age_days": 1,
"max_age_days": 2,
"source": "coinmarketcap_csv",
"row_count": 5871,
"methodology_version": "crypto-scout-canonical-v1.1"
}
}
What it does
- Computes a daily
0.0–1.0Bitcoin risk metric from the canonicalcollector/btc-csv/btc_usd_daily.csvhistory. - Shows the latest
low,neutral, orhighstate alongside a two-year risk history chart. - Displays completed-candle HLC3 model price context and a risk-level scenario ladder in
0.025increments. - Publishes a daily brief in English, Russian, Simplified Chinese, German, French, Spanish, and Arabic.
- Exposes read-only analytics endpoints and accepts email waitlist contacts server-side, never in browser storage; users should not submit sensitive information.
What makes it different
- Visible freshness and readiness. The UI shows the latest completed day and validation state;
/api/readinessreturns HTTP 503 when freshness or validation checks fail. - Deterministic and reproducible. A versioned methodology recomputes the metric from the same canonical daily history, with validation metadata recording each import.
- Scenarios, not forecasts. The price ladder runs hypothetical prices through the same model to show where risk levels would change; it is not a prediction or trading instruction.
Current Status
Current operational status, evidence, and accepted limitations: Production Readiness.
For AI agents
Start with the repository llms.txt. This branch defines the machine-readable /api/openapi.json endpoint; deployment remains pending operator work. Use the Agent Access Pack for endpoint examples, cache semantics, and interpretation boundaries.
Agents must call /api/readiness first, bind reported values to its dates and freshness state, and preserve the analytics-not-advice framing.
Architecture
| Service | Stack | Purpose |
|---|---|---|
timescaledb | TimescaleDB/PostgreSQL | BTC OHLCV, risk rows, validation state, brief snapshots, waitlist leads |
data-collector | Python, asyncpg, APScheduler, httpx | Daily CSV refresh, full CSV import, risk recomputation |
backend | FastAPI, asyncpg | API, readiness, waitlist storage, risk and brief reads |
frontend | React, Vite, ECharts, nginx | Public seven-locale interface and API proxy |
flowchart LR
Source[CoinMarketCap public download<br/>or optional API] --> CSV[Canonical BTC daily CSV]
Schedule[Daily collector schedule] --> Collector[data-collector]
CSV --> Collector
Collector --> DB[(TimescaleDB)]
DB --> API[FastAPI backend]
API --> UI[React frontend]
API --> Agents[AI agents and API clients]
The canonical CSV remains the durable source of truth; the collector refreshes and validates it, recomputes risk, and writes the daily snapshot consumed by the API.
Quick Start
cp .env.example .env
./scripts/manage.sh validate
./scripts/manage.sh start
./scripts/manage.sh migrate
./scripts/manage.sh backfill
Open: http://localhost:3001
Documentation
- Documentation index
- Product overview
- Risk methodology
- Architecture
- API reference
- Freshness and validation
- Agent documentation
- Operations and production evidence
Disclaimer and licence
Bitcoin Risk Brief provides analytics and research context only. It is not financial advice, investment advice, a price forecast, or a trading recommendation.
Owned source code, documentation, and configuration are licensed under Apache-2.0. Bundled third-party BTC/USD market data remains subject to source-provider terms; see NOTICE.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.