library_search
One search over concepts (alias-aware) and indicators
How to use it
library_search is exposed by the Luxalgo MCP Server MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the library_search tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Luxalgo MCP Server
npx -y @luxalgo/mcpOther tools in Luxalgo MCP Server (33)
Connected accounts: broker, currency, equity, cash
Open positions with market values, asset class, entry price; negative quantity means short
Bypass the 5-minute cache and re-fetch now
Supported brokers, their env vars (set or unset, never values), read-only key guides
Total equity, equity by broker, top positions, FIFO win rate and realized PnL
Trade history, newest first; filter by broker or symbol
The catalog of precomputed questions, each stating in plain language what its number means
One result in the engine's full honesty envelope: estimate, N, Wilson 95% CI, minimum-sample guards, stability split, per-year counts, distribution, disclaimer
What the hosted store covers: symbols, session calendars, coverage windows, last build
Full concept page as markdown
A family hub as markdown plus concept roster
Indicator detail: body, family, concepts, source code availability
Full source code when publicly served, fetched only on demand
Paginated concept roster, optionally per family
The taxonomy backbone with counts
Filtered, paginated browse (family, concept, tags, platform, tier) with server-side sort
The indicator tag vocabulary, for the tags filter
One challenge's full encoded ruleset (drawdown modes, consistency, payout gating, citations), editable and re-simulatable inline
Same trader across up to 12 challenges, EV-sorted (not a ranking)
One firm's full dossier: profile, every challenge, live offers, written overview
Every simulatable firm and challenge in the live directory, provenance-disclosed
Risk sweep: pass-optimal vs EV-optimal risk per trade (they differ)
The site's reference-archetype odds, recomputed live (seed 42, 10k paths)
Search firms; firm filters (platforms, markets, payments, Trustpilot, country availability) compose with nested challenge and offer filters, and include nests matching children
Search challenges by rules (size, fee, steps, profit split, drawdown, trading restrictions) and parent firm; can attach applicable live offers
Current discounts and promo codes, resolvable per firm or per challenge
Monte Carlo of your stats (win rate, avg win, trades/day, risk sizing) through a firm's exact ruleset and funded horizon: pass probability with CI, which rule kills attempts, expected attempts and cost, EV, payout probability
Same, from your real R-multiple trade series; block bootstrap preserves your streaks
Screen one strategy across every simulatable challenge against an explicit pass bar
The catalog: every dataset's row count, freshness, years with data (live vs deep-history archive), ticker-searchability; pass dataset for its field roster, filterable paths, caveats, per-year coverage, source health and dump URLs
The newest daily delta of a dataset (today's insider filings, this week's congressional disclosures), optionally narrowed by ticker or text
Search one dataset by ticker, free text, exact field values (where, dot paths) and event-date range, choosing which years to read; newest/oldest ordering with paging
One ticker across every ticker-bearing dataset for a year: per-dataset counts with the newest rows — a public-record dossier