Macro Lab
Macro Lab v1.3.3
한국·미국 거시경제 데이터를 AI로 직접 분석
From the developer
Declared limitations
- Single-company share prices are out of scope: Macro Lab holds macro series and market indices, not individual stock quotes. The app should not be invoked.
- Cryptocurrency prices are out of scope: Macro Lab carries no crypto series. The app should not be invoked.
- Rental listings are out of scope: Macro Lab holds recorded apartment sales, not listings of homes for rent. The app should not be invoked.
Not specified in the available declarations: capabilities, pricing & account requirements.
Onboarding example
Using Macro Lab data, chart Korean 3-year KTB yields against the US 2-year yield since 2020 and say what moved first.
Sources & dates
Developer declarations; not independently tested. Listing last checked Nov 16, 2026. Package observed Nov 15, 2026.
Description
From the marketplace listing
Macro Lab (macrolab.kr) opens its public-licence macro data to its members' AI agents (the server signs you in once through OAuth): 200+ monthly series for Korea, the US and global markets since 2001 (ECOS, FRED, R-ONE, 국토교통부 실거래가) plus public daily twins and the 국토교통부 apartment sales of every Seoul complex since 2006. Read-only MCP tools (search, series, daily, latest, statistics, rate decisions, apartment complexes) and a skill that explains how to read each column, which unit and benchmark apply, and how to report a relationship without over-claiming. Models, forecasts and the track record of Macro Lab are not part of the data.
Language: English · Automatically detected from descriptions.
Changes
No changes recorded yet. Follow this plugin to keep track of future changes.
First seen Nov 12, 2026. Last seen Nov 16, 2026.
Similar plugins
Find competitors to follow as you develop your plugin.
-
Read-only access to BadOnion (나쁜양파) data: monthly trade statistics by HS code for 26 economies, company financials, producer price indice...
Shared terms: credit, growth, korea, korean
-
Give ChatGPT access to your community's vibe. Vibewatch is community intelligence for web3 teams: it reads your community across Discord,...
Shared terms: daily, sentiment, server, market
-
Cargo is GTM infrastructure for AI assistants. Connect this MCP server and ChatGPT can operate your Cargo workspace: discover and run act...
Shared terms: credit, oauth, server, sale
-
Log trades and journal notes in your Financial Tech Wiz Trading Journal and ask about your trades, statistics, accounts and equity, plus ...
Shared terms: member, money, part, plus
-
Tremor Watch: how many market relationships stopped behaving this week.
Shared terms: commoditie, credit, forecast, reading
Keywords
Files & skills
File archives
Skill instructions
macrolab-data12.3 KB
--- name: macrolab-data description: Analyse Korean and US macro data from Macro Lab (macrolab.kr) — interest rates, inflation, growth, money, credit, FX, stocks, commodities, housing, sentiment, AI and startup series, monthly since 2001 plus daily twins, and Seoul apartment sales by complex (단지별 실거래, 2006 on). Use when a question needs Korean/US economic time series (금리·물가·성장·환율·주가·부동산 등), one Seoul apartment complex's prices, a relationship between two indicators, where an indicator stands today, or a chart/table from this data. Reads the public-licence data through the Macro Lab MCP tools (members; OAuth). --- # Macro Lab data Macro Lab (macrolab.kr) collects Korean and US macro series from ECOS (한국은행), FRED, 한국부동산원 (R-ONE) and 국토교통부 실거래가, and opens the **public-licence part** of it to its members' AI agents through its MCP server (the server signs the member in through OAuth the first time an agent connects). This skill tells you how to get the data, how to read each series without misreading it, and how to report what you find. What you get, through the MCP tools: the monthly panel (one value per series per month, `YYYY-MM`, 2001-01 onward), the data dictionary (what every series is), public daily / weekly twins of the headline series (US Treasury yields, the Fed funds rate, oil, the dollar, Korean rates, the won, the KOSPI …), every Bank of Korea monetary policy board and FOMC rate decision since 2001, holds included, and the 국토교통부 apartment sales of every Seoul complex since 2006 (per month and size type: the count, the median, the median per ㎡, plus the latest individual sales). The panel is rebuilt monthly, the daily data twice a day, the apartment sales daily. Every call answers a capped window — there is no bulk download. What you do NOT get: Macro Lab's models, rules, forecasts and track record, derived variables, and series whose owner restricts redistribution (Nasdaq, Cboe VIX, Moody's, Coinbase, U. Michigan, individual stock prices). Do not claim any of those from this data. ## 1. Get the data Use the MCP tools in this order — `list_datasets` (what exists, the rules, the daily ids) → `search_variables` (ids by Korean or English words, group or country) → `get_series` for monthly values, `get_daily` for daily twins, `latest` for "지금", `describe_variable` for one series in full. Every call is capped (12 ids × 600 months, 8000 cells; 8 daily ids × 600 rows), so ask for the window the question needs: the last 120 months by default, `from`/`to` or `last` to move. The resources `macrolab://dictionary.json` (every series' entry) and `macrolab://series/<id>.csv` (one series' history) give one piece at a time. Do not copy rows out of a tool answer to calculate with them — let the server calculate: `compute` resamples (daily → weekly or monthly), transforms (`diff`, `pct`, `log`, `yoy_pct`, `yoy_diff`, or `auto` = the dictionary's unit), and returns summary statistics, a correlation matrix with leads and lags (`max_lag`), an OLS with Newey–West t (`regress`, x lagged by `lag`) or event windows (`events: bok_mpc` / `fomc`, optionally `decision: hold`, or your own `event_dates`) — small answers whatever the history length. `get_decisions` lists the BOK and FOMC decisions themselves (a hold leaves no trace in the rate series). With `get_daily`, `align: common` keeps only the dates every requested series has. One Seoul apartment complex: `find_apartments` (part of the name in Korean — 은마, 헬리오시티, 잠실주공5단지; or a 구 / 법정동 alone for that area's most traded complexes) gives its id, the 동, the year built and the size types sold; `get_apartment_trades` (the id; `area` = one size type, `from`/`to`, `period` month · quarter · year, `sales` = how many of the latest individual sales to list, 0–200) gives the table and the latest sales. Two complexes are two calls — compare the same size type. If you can run code (Claude Code, Codex, a notebook), keep what a tool answered in a local file for the session and calculate there when `c
Preview of the first 4,000 characters. Read full instructions →
Release notes
1.3.3: first public version. Ten read-only tools (list_datasets, search_variables, describe_variable, get_series, get_daily, latest, compute, get_decisions, find_apartments, get_apartment_trades), three resources and the macrolab-data skill; the data comes as capped tool answers, with no bulk download.
Declared in the saved package. Remote tools may change independently.
Package details
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
- Package license
- MIT
- Package author
- Macro Lab
- Keywords
- See keywords
- Commerce declaration
- Does not support commerceThis does not establish whether access is free or paid.
- Review scenarios
- 5 positive · 3 negativeScenario counts, not test results.
Package observed Nov 15, 2026.
Technical details
- First seen
- Nov 12, 2026 · 00:00 UTC
- Last seen
- Nov 16, 2026 · 00:00 UTC
- Collection status
- Collected
plugin_asdk_app_6af24e1cc1c88191b5f601414f994911
Download plugin data (JSON)Plugin details: freshly prepared. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.