closelook-intelligence
Closelook AI-market intelligence: 5 indices, 6 ranking families, stock snapshots. 13 tools.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"closelook-intelligence": {
"url": "https://closelook-mcp.look-investment-gmbh.workers.dev/mcp"
}
}
}Remote endpoints
https://closelook-mcp.look-investment-gmbh.workers.dev/mcpstreamable-httpWhat it can do
Tool inventory
Tools (30)
🟢search_closelook(query, type)
Search Closelooknet’s research corpus: 101 explainers, glossary, heresies (contrarian theses), reports, strategy notes and the finance library. Returns matching pieces with a one-line summary and link. Use for "what has Closelooknet written about X".
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Keywords, e.g. \"memory supercycle\" or \"sector rotation\""
},
"type": {
"type": "string",
"enum": [
"all",
"101",
"glossary",
"heresy",
"report",
"strategy",
"library"
],
"description": "Restrict to one content type (default all)"
}
},
"required": [
"query"
]
}🟢define_term(term)
Get Closelooknet’s definition of a financial or market term from its 260+ entry glossary (classic finance, chart indicators, options, Elliott-wave vocabulary, and Closelooknet-coined concepts like the Numerator Regime or Constraint Relay). Concepts without a glossary entry fall back to the 101 explainers (e.g. Memory Wall, CapEx Cliff).
Input Schema
{
"type": "object",
"properties": {
"term": {
"type": "string",
"description": "The term, e.g. \"Korea discount\" or \"MACD\""
}
},
"required": [
"term"
]
}🟢get_index_snapshot(index)
Current snapshot of one proprietary Closelooknet index: RUBIN (AI buildout), HALO (non-AI growth), AW40 (AI deployment), AEI (agentic stack), AIU (AI users — companies putting AI to work in an existing business) or EUROAI. Returns level, recent returns and the strongest/weakest sub-indices, end-of-day.
Input Schema
{
"type": "object",
"properties": {
"index": {
"type": "string",
"enum": [
"RUBIN",
"HALO",
"AW40",
"AEI",
"AIU",
"EUROAI"
],
"description": "Index code"
}
},
"required": [
"index"
]
}🟢compare_indices
Side-by-side of all Closelooknet headline indices (Rubin, HALO, AW40, AEI, AI Users, Euro-AI): last close, 1-day, 1-week and month-to-date returns. The fastest read on where the AI trade rotated, end-of-day.
Input Schema
{
"type": "object",
"properties": {}
}🟢get_price_history(ticker)
End-of-day price read for any of ~2,500 tickers in Closelooknet’s data lake: latest close, close-to-close changes over 1D/1W/1M/3M/6M/1Y, 52-week range, and the last ten sessions. US tickers bare (NVDA), foreign with exchange suffix (005930.KS, 6857.T, ASML.AS).
Input Schema
{
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "Ticker, e.g. NVDA or 005930.KS"
}
},
"required": [
"ticker"
]
}🟢get_signal_scores(ticker)
Closelooknet’s proprietary per-ticker scoring for ~900 scored stocks: composite rank, the seven sub-scores (quality, growth, valuation, balance, cash quality, capital allocation, momentum) under the sector-appropriate weight set, plus literature ratios (Altman Z, Piotroski F, Beneish M). End-of-day.
Input Schema
{
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "Ticker, e.g. DDOG"
}
},
"required": [
"ticker"
]
}🟢get_print_record(ticker)
Closelooknet’s Print Record for a covered ticker: the last ~10 earnings prints with EPS/revenue beat-or-miss and the 3-day price reaction, headline counts (how often beats were actually PAID), the curated metric line and the next scheduled print. The gap between beat-rates and reactions is the product. Call without a ticker to see current coverage and the forward calendar.
Input Schema
{
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "Ticker, e.g. LITE or NBIS. Omit to list coverage."
}
}
}🟢get_factor_regime
Closelooknet’s factor-regime read: the momentum/low-volatility ratio (SPMO vs SPLV) against its 50-day trend — which factor is leading, how stretched the ratio is (3-year percentile), and the 20/60-day rate of change. The fastest single read on risk appetite under the index surface. End-of-day.
Input Schema
{
"type": "object",
"properties": {}
}🟢get_credit_stress
Closelooknet’s AI Credit Stress Tape: where stress sits on the six-rung funding ladder of the AI buildout (from balance-sheet-funded hyperscalers down to project-funded neoclouds), FRED credit spreads (IG/BBB/B/HY with 20/60-day deltas and 3-year percentiles), tier aggregates (FCF coverage, external-funding ratio, interest coverage) and per-issuer warning flags. End-of-day.
Input Schema
{
"type": "object",
"properties": {}
}🟢get_df_ranking(view, limit)
Closelooknet’s Directional Flow ranking: the nightly trend-quality score (recency-weighted regression on log-closes, ~330 covered stocks) ranked seven ways — top scores, rising fastest (21d), this week’s biggest moves (5d), steadiest builders (63d), still getting stronger, getting weaker, falling fastest. Mirrors closelook.net/stocks/rankings/directional-flow/. End-of-day.
Input Schema
{
"type": "object",
"properties": {
"view": {
"type": "string",
"enum": [
"top",
"momentum",
"short-term",
"quarter",
"accelerating",
"weakening",
"falling-fastest"
],
"description": "Which ranking cut (default: top = highest scores)"
},
"limit": {
"type": "number",
"description": "Rows to return, 1–25 (default 10)"
}
}
}🟢get_ranking(family, view, limit)
Closelooknet’s other daily ranking families (siblings of get_df_ranking, end-of-day): country-flow / sector-flow / theme-flow (the Directional Flow trend score over ~72 market cuts via US-listed ETFs; views: top, momentum), up-down-beta (up-day beta vs down-day beta over 126 trading days across ~2,700 stocks; views: leaders, fragile, unstable), etf-dispersion (40 funds ranked by how far apart their members’ returns are; views: divided, today, broadest). Mirrors closelook.net/stocks/rankings/.
Input Schema
{
"type": "object",
"properties": {
"family": {
"type": "string",
"enum": [
"country-flow",
"sector-flow",
"theme-flow",
"up-down-beta",
"etf-dispersion"
],
"description": "Which ranking family"
},
"view": {
"type": "string",
"description": "Family-specific cut. Cuts: top (default) | momentum. up-down-beta: leaders (default) | fragile | unstable. etf-dispersion: divided (default) | today | broadest."
},
"limit": {
"type": "number",
"description": "Rows to return, 1–25 (default 10)"
}
},
"required": [
"family"
]
}🟢get_stock_snapshot(ticker)
One covered stock through Closelooknet’s own engines, end-of-day: the Directional Flow trend score with its 5/21/63-day score changes and trend state, up-day vs down-day beta with the engine’s structural state (healthy leader / fragile / distribution / decoupling), and Closelooknet index memberships. Pair with get_price_history for bars and get_signal_scores for the quality-score panel.
Input Schema
{
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "Ticker as displayed on closelook.net, e.g. NVDA, ASML, 8035"
}
},
"required": [
"ticker"
]
}🟢get_tech_board(region, limit)
Closelooknet’s Tech Signal Board: what is hot in global tech right now, ranked into one board — new highs, big moves, analyst-target gaps, sector rotation and cooling reads, mixing stocks, sectors and indices across the US, Europe and Asia. Each card carries its own session and as-of date. Mirrors closelook.net/signals/board/ (dated archive at /signals/board/archive/). Refreshed after each close.
Input Schema
{
"type": "object",
"properties": {
"region": {
"type": "string",
"description": "Optional region filter, e.g. US, Germany, Korea, Hong Kong, Japan"
},
"limit": {
"type": "number",
"description": "Cards to return, 1–20 (default 10)"
}
}
}🟢get_wire(wire, ticker, limit)
Closelooknet’s two US wires. wire=analyst: the latest sell-side calls (upgrades, downgrades, initiations, price-target moves), newest first, each with the house read where the name is covered (index/portfolio membership, 50/200-day state, Street consensus). wire=earnings: the latest prints against consensus EPS (beat / miss / in line with the surprise) plus the forward calendar. Mirrors closelook.net/signals/analysts/ and /signals/earnings/ (per-day archives under /archive/). Refreshed several times per trading day.
Input Schema
{
"type": "object",
"properties": {
"wire": {
"type": "string",
"enum": [
"analyst",
"earnings"
],
"description": "Which wire (default: analyst)"
},
"ticker": {
"type": "string",
"description": "Optional ticker filter, e.g. NVDA"
},
"limit": {
"type": "number",
"description": "Rows to return, 1–25 (default 10)"
}
}
}🟢get_money_temperature
Closelooknet’s Money Temperature: the house money-regime monitor — eight instruments (SPY, QQQ, IWM, TLT, HYG, GLD, UUP, BTC) scored 0–100 on Position / Momentum / Volume / Volatility / Fragility, each with its technical state, plus the absorption ratio. Mirrors closelook.net/lab/temperature/. Daily.
Input Schema
{
"type": "object",
"properties": {}
}🟢get_macro_regime(monitor)
Closelooknet’s two leading macro monitors in one read: Structural Inflation (26 FRED series, 7 buckets — score, regime, direction, structural-vs-transitory, supply shock) and Growth & Recession (~19 FRED series, 5 buckets — score, regime, direction, recession risk), each with bucket-level z-scores. Mirrors closelook.net/lab/macro/inflation/ and /lab/macro/growth/. Daily on FRED release days.
Input Schema
{
"type": "object",
"properties": {
"monitor": {
"type": "string",
"enum": [
"both",
"inflation",
"growth"
],
"description": "Which monitor (default both)"
}
}
}🟢get_sector_matrix(window, region)
Closelooknet’s Global Sector Engine: eleven GICS sectors × four regions (US, Europe, Asia-Pac DM, EM) returns over one window (5d, 1m, 3m, ytd), with leaders and laggards per region and per sector. The decomposition institutions see; via ETF vehicles, EM approximated from country funds. Mirrors closelook.net/lab/sectors/. Daily after each regional close.
Input Schema
{
"type": "object",
"properties": {
"window": {
"type": "string",
"enum": [
"5d",
"1m",
"3m",
"ytd"
],
"description": "Return window (default 1m)"
},
"region": {
"type": "string",
"enum": [
"US",
"Europe",
"AsiaPacDM",
"EM"
],
"description": "Optional single region"
}
}
}🟢get_sovereign_pressure
Closelooknet’s Sovereign Pressure board: G7 ten- and thirty-year government yields aggregated equal- and debt-weighted, the 10s30s and 2s10s slopes, per-country 2Y/10Y/30Y with 1-day and 21-day changes, and the z-scored Pressure Index (high = broad, long-end-led sovereign sell-off). Mirrors closelook.net/lab/sovereign-pressure/. Daily.
Input Schema
{
"type": "object",
"properties": {}
}🟢get_mag_pulse
Closelooknet’s Mag Pulse: the daily board on the hyperscaler cohort — the Mag names with 1d/1w/1m/1y changes by cohort, the benchmarks (QQQ, SPY, SOXX, XLK, IGV, MAGS), the MAGS trendline read and the ORCL torque. Mirrors closelook.net/lab/mag-pulse/. Daily 22:30 UTC.
Input Schema
{
"type": "object",
"properties": {}
}🟢get_ratio_pair(pair)
Closelooknet’s Ratio Chart presets: relative-performance facts for ten pairs — India vs US (Nifty 50 / S&P 500, INDA / SPY), EM vs US (EEM / SPY), developed ex-US vs US (EFA / SPY), Japan vs US (Nikkei / S&P), growth without tech (QQXT / QQQ), health care vs tech (XLV / XLK), low-vol vs momentum (SPLV / SPMO), gold vs US equities (GLD / SPY), bitcoin vs S&P 500. Per pair: current ratio, 1y change, all-time low/high with dates, percentile in its own history, distance from the low, lowest-since date. Weekly since each pair’s first common date. Mirrors closelook.net/lab/ratio/ (where any pair can be charted).
Input Schema
{
"type": "object",
"properties": {
"pair": {
"type": "string",
"description": "Preset slug (nifty-spx, inda-spy, eem-spy, efa-spy, n225-spx, qqxt-qqq, xlv-xlk, splv-spmo, gld-spy, btc-spx) or omit for all"
}
}
}🟢get_portfolio_summary(book)
Closelooknet’s live reference portfolios (the public snapshot): for each book — AI Build-Out, Hypergrowth, Global Tech 50, Global ETFs, Derivatives, and the index trackers (Rubin EW, Rubin Momentum, Rubin Sector Rotation, Jensen, T1) — the snapshot date, position count, the top-10 holdings by weight and the headline return vs deposited capital. Exactly what the free page shows; full composition, cost basis and P&L are subscriber-only. Mirrors closelook.net/portfolios/. Weekly (Friday close).
Input Schema
{
"type": "object",
"properties": {
"book": {
"type": "string",
"description": "Book slug (ai-buildout, hypergrowth, global-tech-50, global-etfs, derivatives, rubin-ew, rubin-momentum, rubin-sector-rotation, jensen, t1); omit for all"
}
}
}🟢get_tape(window, type, limit)
Closelooknet’s Tape: timestamped, deterministic market cards — session wraps (Asia / Europe / US / after-hours), macro prints, earnings reactions, outliers, PEAD signals and weekly recaps — newest first, each with headline, excerpt and body. Mirrors closelook.net/tape/. Mon–Fri live; fully automated surface (disclosed as such).
Input Schema
{
"type": "object",
"properties": {
"window": {
"type": "string",
"description": "Optional window filter: ASIA, EU, US, AH, PRE"
},
"type": {
"type": "string",
"description": "Optional card type: B1 (session), B2 (macro/recap), C (earnings/PEAD), D (outlier)"
},
"limit": {
"type": "number",
"description": "Cards to return, 1–20 (default 8)"
}
}
}🟢get_chart_pick(date, all)
Closelooknet’s Weekly Chart Pick: one standout name from the Directional Flow engine each week, worked through by hand — the setup bullets, the house reading and the STANDING closing forecasts (diary views, scored afterwards). Mirrors closelook.net/chart-pick/. Weekly (Friday).
Input Schema
{
"type": "object",
"properties": {
"date": {
"type": "string",
"description": "Optional YYYY-MM-DD of a specific pick; omit for the latest"
},
"all": {
"type": "boolean",
"description": "Return every published pick (summaries)"
}
}
}🟢get_market_instrument(symbol)
Closelooknet’s market board instruments — the indices, FX pairs, crypto, futures proxies and US funds on the homepage board (S&P 500, Nasdaq-100, Nikkei, KOSPI, TAIEX, HSI, Nifty, DAX, EURUSD, USDJPY, BTC, gold, oil …): last level, 1d/1m/3m/YTD/1y changes and the 52-week range from three years of daily closes. Mirrors closelook.net/markets/<slug>/. Daily after the US close.
Input Schema
{
"type": "object",
"properties": {
"symbol": {
"type": "string",
"description": "Vendor symbol or label fragment, e.g. N225.INDX, Nikkei, EURUSD, BTC; omit to list the board"
}
}
}🟢get_day_hub(date, days)
Closelooknet’s trading-day hub: for a given date (or the latest), the day’s Morning 10 headline, Midday 10 headline and Daily Pulse edition(s) with links — the same pieces closelook.net/days/<date>/ ties together. Last 90 trading days.
Input Schema
{
"type": "object",
"properties": {
"date": {
"type": "string",
"description": "YYYY-MM-DD; omit for the latest day with content"
},
"days": {
"type": "number",
"description": "Return the last N days as a list (1–14)"
}
}
}🟢get_latest_view
Closelooknet’s latest published market view: today’s Morning 10 (ten-point daily overview) and the latest Daily Pulse thesis, each with headline, core statement and link to the full piece.
Input Schema
{
"type": "object",
"properties": {}
}🟢brief(task, can_pay, budget, horizon, universe)
Send the WHOLE task first, in one sentence (e.g. "compare SK Hynix and Samsung memory exposure over months"). Returns which tickers, indices and topics Closelooknet recognised, the free route through its pages and JSON twins in order, the paid one-call shortcut with its price where one exists, and the questions that would narrow the task. No model runs; nothing is charged. Use before fetching pages one by one.
Input Schema
{
"type": "object",
"properties": {
"task": {
"type": "string",
"description": "The whole task, 3–1,000 characters"
},
"can_pay": {
"type": "boolean",
"description": "Whether you can pay per call over HTTP 402 (USDC or card)"
},
"budget": {
"type": "number",
"description": "USD you may spend on this task"
},
"horizon": {
"type": "string",
"description": "e.g. today, weeks, months, years"
},
"universe": {
"type": "string",
"description": "Tickers, one Closelooknet index, or a region"
}
},
"required": [
"task"
]
}⚪open_session(task)
Opens a multi-turn research session (private beta, free) with a moderator and the Closelooknet research seat. Give the whole task; returns a session_id. Then use session_message to ask research questions. Questions that need a personal recommendation move the session to advice_required (no licensed advisor is connected yet). Not investment advice.
Input Schema
{
"type": "object",
"properties": {
"task": {
"type": "string",
"description": "The whole task, 3–1,000 characters"
}
},
"required": [
"task"
]
}⚪session_message(session_id, text)
Sends a research question into an open Closelooknet session. The answer cites each figure with its cl: source and data date; wording by AI is marked with the model. If the question needs a personal recommendation, the session moves to advice_required and lists the next actions.
Input Schema
{
"type": "object",
"properties": {
"session_id": {
"type": "string",
"description": "From open_session (ses_…)"
},
"text": {
"type": "string",
"description": "The question"
}
},
"required": [
"session_id",
"text"
]
}⚪session_action(session_id, action)
Moves a Closelooknet session on: continue_research_only (after advice_required), request_advisor (answers advisor_unavailable until a licensed advisor is connected), finish_research or complete. Returns the new state and the moderator note.
Input Schema
{
"type": "object",
"properties": {
"session_id": {
"type": "string",
"description": "From open_session (ses_…)"
},
"action": {
"type": "string",
"enum": [
"continue_research_only",
"request_advisor",
"start_research",
"finish_research",
"complete"
]
}
},
"required": [
"session_id",
"action"
]
}Community
Evidence