CLI
Every endpoint as a command that prints JSON to stdout — pipe it into
jq, an LLM, or a bot. Zero third-party dependencies (Python
3.8+ stdlib only). Built for trading agents and shell pipelines.
Why a CLI when there's an MCP server?
The MCP server is for agents inside Claude Desktop,
Cursor, and Cline. The CLI is the better fit when you're driving a
bot or shell pipeline: plain JSON with no protocol envelope
is more token-efficient, it composes with Unix tools, and it runs anywhere
curl does. Same data, both surfaces.
Install
pip install n0brains-cli
export N0BRAINS_API_KEY=intel_sk_... # get one at n0brains.com
Public endpoints (like proof) work without a key. Everything
else reads N0BRAINS_API_KEY (or --api-key).
Commands
| Command | Returns |
|---|---|
signals | Active classified signals (--proven-only, --tradeable-only, --asset, --type, --limit) |
signal <id> | One signal with full context |
similar <query> | Semantic similarity search (pro) |
levels <coin> | Support/resistance |
liquidation-map <coin> | Estimated liquidation-cluster zones |
correlation [coin] | Correlation matrix, or one coin's corr+beta (--vs, --coins) |
rotation | Altseason/rotation read |
macro | Daily BTC/ETH macro bias |
narrative <coin> | Narrative context |
trust <coin> | Trust/rug score |
manipulation <coin> | Manipulation score |
proof [--equity] | Live forward-return proof per signal type (+ equity curve) |
performance [--days N] [--tier N] | Backtest stats |
stream | Live signal stream over WebSocket (pro) |
Examples
# Only proven-edge signals, as JSON
n0brains signals --proven-only --limit 10
# Is it altseason? one-line answer
n0brains rotation | jq -r .regime
# Where are BTC liquidation magnets?
n0brains liquidation-map BTC | jq '.densest_long_liq_zone, .densest_short_liq_zone'
# Live forward-return proof
n0brains proof
# Stream proven strong-conviction signals into a bot (needs: pip install websockets)
n0brains stream | jq -c 'select(.conviction=="strong")'
Exit code is 2 on an API error (so scripts can detect
failures), 0 on success. For agent frameworks, the
SKILL.md shipped with the CLI describes each tool and how to
use the proven-edge gate.