Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.closelookventure/closelook-intelligence

REMOTE · CLOSELOOK-MCP.LOOK-INVESTMENT-GMBH.WORKERS.DEV

Closelook AI-market intelligence: 5 indices, 6 ranking families, stock snapshots. 13 tools.

−1 this week 80 Trust /100

Last scanned (23 hours ago)

Scores higher than 81% of remote servers

Reachable. Last reached 4 Nov 2026.

Category Finance and Payments

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability84
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 3754 tokens (~125/item across 30 items; 30 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
  • Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage99
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 98% of tool parameters carry a description.Partial
Tool Safety88
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 1 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "brief" implies "send" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
  • An AI judge read all 31 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 4 Nov 26 0
    • Stability: pass → 0.97 functional
  • 3 Nov 26 −1
    • Schema quality: 3306 → 3754 ▼ functional
    • Destructive annotations: pass → 50 functional
    • Server version: 0.9.5 → 0.9.7 functional
    • New tool “brief” functional
    • New tool “open_session” functional
    • New tool “session_action” functional
    • New tool “session_message” functional
  • 25 Oct 26 0
    • Tool “compare_indices” rewrote its description, which is the text the model reads security
    • Tool “get_index_snapshot” rewrote its description, which is the text the model reads security
    • Server version: 0.9.4 → 0.9.5 functional
  • 19 Oct 26 0
    • Tool “define_term” rewrote its description, which is the text the model reads security
    • Tool “get_signal_scores” rewrote its description, which is the text the model reads security
    • Server version: 0.9.1 → 0.9.4 functional
  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 9 Sept 26 0
    • Stability: 0.97 → pass security
  • 26 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 4 Nov 2026 · Probed https://closelook-mcp.look-investment-gmbh.workers.dev/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=look-investment-gmbh.workers.dev CN=WE1,O=Google Trust Services,C=US 8 Oct 2026 6 Jan 2027 ECDSA 256 ECDSA-SHA256 cc87888a535349800ed3a04588720bef
SANs: look-investment-gmbh.workers.dev, *.look-investment-gmbh.workers.dev
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of closelook-mcp.look-investment-gmbh.workers.dev. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
dev. present 60074 8 Verified
workers.dev. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://closelook-mcp.look-investment-gmbh.workers.dev/mcp Verified 200
http (plaintext) http://closelook-mcp.look-investment-gmbh.workers.dev/mcp Inconclusive 405
MCP tools · 30 exposed · ~3,686 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
brief ~189

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.

NameTypeReqDescription
budgetnumber–USD you may spend on this task
can_payboolean–Whether you can pay per call over HTTP 402 (USDC or card)
horizonstring–e.g. today, weeks, months, years
taskstringyesThe whole task, 3–1,000 characters
universestring–Tickers, one Closelooknet index, or a region

No output schema declared.

No examples provided.

compare_indices ~69

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 present but exposes no named parameters.

No output schema declared.

No examples provided.

define_term ~105

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).

NameTypeReqDescription
termstringyesThe term, e.g. "Korea discount" or "MACD"

No output schema declared.

No examples provided.

get_chart_pick ~103

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).

NameTypeReqDescription
allboolean–Return every published pick (summaries)
datestring–Optional YYYY-MM-DD of a specific pick; omit for the latest

No output schema declared.

No examples provided.

get_credit_stress ~104

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 present but exposes no named parameters.

No output schema declared.

No examples provided.

get_day_hub ~108

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.

NameTypeReqDescription
datestring–YYYY-MM-DD; omit for the latest day with content
daysnumber–Return the last N days as a list (1–14)

No output schema declared.

No examples provided.

get_df_ranking ~135

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.

NameTypeReqDescription
limitnumber–Rows to return, 1–25 (default 10)
viewstring–Which ranking cut (default: top = highest scores)

No output schema declared.

No examples provided.

get_factor_regime ~83

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 present but exposes no named parameters.

No output schema declared.

No examples provided.

get_index_snapshot ~96

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.

NameTypeReqDescription
indexstringyesIndex code

No output schema declared.

No examples provided.

get_latest_view ~50

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 present but exposes no named parameters.

No output schema declared.

No examples provided.

get_macro_regime ~122

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.

NameTypeReqDescription
monitorstring–Which monitor (default both)

No output schema declared.

No examples provided.

get_mag_pulse ~99

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 present but exposes no named parameters.

No output schema declared.

No examples provided.

get_market_instrument ~162

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.

NameTypeReqDescription
symbolstring–Vendor symbol or label fragment, e.g. N225.INDX, Nikkei, EURUSD, BTC; omit to list the board

No output schema declared.

No examples provided.

get_money_temperature ~91

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 present but exposes no named parameters.

No output schema declared.

No examples provided.

get_portfolio_summary ~175

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).

NameTypeReqDescription
bookstring–Book slug (ai-buildout, hypergrowth, global-tech-50, global-etfs, derivatives, rubin-ew, rubin-momentum, rubin-sector-rotation, jensen, t1); omit for all

No output schema declared.

No examples provided.

get_price_history ~119

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).

NameTypeReqDescription
tickerstringyesTicker, e.g. NVDA or 005930.KS

No output schema declared.

No examples provided.

get_print_record ~113

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.

NameTypeReqDescription
tickerstring–Ticker, e.g. LITE or NBIS. Omit to list coverage.

No output schema declared.

No examples provided.

get_ranking ~208

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/.

NameTypeReqDescription
familystringyesWhich ranking family
limitnumber–Rows to return, 1–25 (default 10)
viewstring–Family-specific cut. Cuts: top (default) | momentum. up-down-beta: leaders (default) | fragile | unstable. etf-dispersion: divided (default) | today | broadest.

No output schema declared.

No examples provided.

get_ratio_pair ~254

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).

NameTypeReqDescription
pairstring–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

No output schema declared.

No examples provided.

get_sector_matrix ~124

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.

NameTypeReqDescription
regionstring–Optional single region
windowstring–Return window (default 1m)

No output schema declared.

No examples provided.

get_signal_scores ~94

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.

NameTypeReqDescription
tickerstringyesTicker, e.g. DDOG

No output schema declared.

No examples provided.

get_sovereign_pressure ~107

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 present but exposes no named parameters.

No output schema declared.

No examples provided.

get_stock_snapshot ~124

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.

NameTypeReqDescription
tickerstringyesTicker as displayed on closelook.net, e.g. NVDA, ASML, 8035

No output schema declared.

No examples provided.

get_tape ~161

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).

NameTypeReqDescription
limitnumber–Cards to return, 1–20 (default 8)
typestring–Optional card type: B1 (session), B2 (macro/recap), C (earnings/PEAD), D (outlier)
windowstring–Optional window filter: ASIA, EU, US, AH, PRE

No output schema declared.

No examples provided.

get_tech_board ~145

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.

NameTypeReqDescription
limitnumber–Cards to return, 1–20 (default 10)
regionstring–Optional region filter, e.g. US, Germany, Korea, Hong Kong, Japan

No output schema declared.

No examples provided.

get_wire ~182

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.

NameTypeReqDescription
limitnumber–Rows to return, 1–25 (default 10)
tickerstring–Optional ticker filter, e.g. NVDA
wirestring–Which wire (default: analyst)

No output schema declared.

No examples provided.

open_session ~93

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.

NameTypeReqDescription
taskstringyesThe whole task, 3–1,000 characters

No output schema declared.

No examples provided.

search_closelook ~105

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".

NameTypeReqDescription
querystringyesKeywords, e.g. "memory supercycle" or "sector rotation"
typestring–Restrict to one content type (default all)

No output schema declared.

No examples provided.

session_action ~78

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.

NameTypeReqDescription
actionstringyes–
session_idstringyesFrom open_session (ses_…)

No output schema declared.

No examples provided.

session_message ~88

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.

NameTypeReqDescription
session_idstringyesFrom open_session (ses_…)
textstringyesThe question

No output schema declared.

No examples provided.

Install

How do I install the io.github.closelookventure/closelook-intelligence MCP server?

io.github.closelookventure/closelook-intelligence is a hosted endpoint at https://closelook-mcp.look-investment-gmbh.workers.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · closelook-mcp.look-investment-gmbh.workers.dev

# add to Claude Code
claude mcp add --transport http closelookventure-closelook-intelligence 'https://closelook-mcp.look-investment-gmbh.workers.dev/mcp'
Common questions

What is the io.github.closelookventure/closelook-intelligence MCP server?

io.github.closelookventure/closelook-intelligence is an MCP server listed in the public MCP registry as io.github.closelookventure/closelook-intelligence. Closelook AI-market intelligence: 5 indices, 6 ranking families, stock snapshots. 13 tools. This page covers its hosted endpoint (https://closelook-mcp.look-investment-gmbh.workers.dev/mcp).

Is the io.github.closelookventure/closelook-intelligence MCP server safe to use?

io.github.closelookventure/closelook-intelligence scores 80 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.closelookventure/closelook-intelligence MCP server expose?

io.github.closelookventure/closelook-intelligence exposes 30 tools: search_closelook, define_term, get_index_snapshot, compare_indices, get_price_history, and 25 more. Their descriptions and schemas cost roughly 3,686 tokens of context every time the server is loaded.

Does the io.github.closelookventure/closelook-intelligence MCP server require authentication?

No. We connected to io.github.closelookventure/closelook-intelligence without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the io.github.closelookventure/closelook-intelligence MCP server still maintained?

io.github.closelookventure/closelook-intelligence is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.