Economy Intel MCP

com.datakootPublished by datakoot.comOfficial publisherv2.1.0Updated Oct 24, 2026

Macro data for AI agents: GDP, inflation, unemployment and more (World Bank, US BLS). No keys.

The publisher's own server: Base Intel MCP

VerifiedStreamable HTTPWeb executableFinanceData & Analytics

Overview

AI-generated overview

Remote MCP server giving assistants keyless World Bank and US BLS macroeconomic data: GDP, inflation, unemployment, trade and more.

What you can do
  • Look up one indicator for a country over recent years, or a snapshot of key indicators for a country
  • Compare a single indicator across several countries for ranking or benchmarking
  • Retrieve key US time series such as unemployment, CPI, nonfarm payrolls, participation, earnings and retail sales
  • List the supported indicators and series to discover what can be queried
When to use it
Useful when an assistant needs to ground answers in official macroeconomic figures mid-task, for country profiles, cross-country comparisons, or US economic series, without signing up for data APIs.
Requirements
Remote streamable HTTP endpoint; no API keys, accounts or environment variables are declared. Network access to the endpoint is required.
Before you install
Read-only data lookups; no writes or credentials are requested. Figures come from third-party public sources (World Bank, US BLS) and are informational only, so verify before relying on them for decisions.

Installation

In SourceWeft

  1. Open Economy Intel MCP in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.datakoot%2Feconomy-gdp-inflation-unemployment/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "economy-intel": {
      "type": "http",
      "url": "https://economy.datakoot.com/mcp"
    }
  }
}

README

Economy Intel MCP — by Datakoot

Macroeconomic data for AI agents — as MCP tools your agent can call mid-task to ground answers in real GDP, inflation, unemployment and trade figures for any country. No API keys.

Tools

ToolWhat it doesSource
country_indicatorAn indicator (GDP, inflation, unemployment, population, ...) for a country over recent yearsWorld Bank
country_profileA snapshot of a country's key macro indicators, latest valuesWorld Bank
compare_countriesRank one indicator across several countriesWorld Bank
us_seriesKey US time series: unemployment, CPI, nonfarm payrolls, participation, earningsUS BLS
list_indicatorsDiscover every indicator and series this server supports—

No API keys required.

Quick start

claude mcp add --transport http economy-intel https://economy.datakoot.com/mcp

Or point any MCP client at https://economy.datakoot.com/mcp.

Grounded, verifiable forecasting

economy-intel is not just data in — it is meant to improve what an agent concludes. To show that, examples/ has a small, legible agent that calls this server's us_series mid-task, projects the next macro print against the market consensus with the arithmetic shown, and submits it to Headline Arena — a public arena where AI-agent forecasts are scored against reality and the calibration is checkable by anyone.

The live version runs the loop the arena's maintainer asked for: it wakes on the data-release calendar, discovers the open macro challenges, grounds each one it can in official US series, and posts a forecast with its reasoning — while skipping the challenges it cannot honestly ground (PPI, PMI, the FOMC rate — anything economy-intel does not serve) instead of guessing. Post on signal, not on a clock.

The point is not a clever model. It is that the inputs are official (World Bank, US BLS), the reasoning is transparent, and the record is public. Run the example yourself — no account, no cost:

python3 examples/datakoot_macro_agent.py cpi

Data & attribution

Country data comes from the World Bank Open Data API (CC-BY 4.0); US series come from the US Bureau of Labor Statistics public data API (US public domain). Informational only.

Part of Datakoot — keyless intelligence APIs for AI agents.

Source: README.md at commit fe6fe0e

Tools

5

country_indicator

Country Indicator

Get a macroeconomic indicator for a country over recent years (World Bank). Indicators: gdp, gdp_per_capita, gdp_growth, inflation, unemployment, population, life_expectancy, exports, imports, govt_debt_pct_gdp, real_interest_rate, fdi, co2_per_capita, internet_users. Country accepts an ISO code (US, DE, JP) or a World Bank country code. You may also pass a raw World Bank indicator code.

Parametersyearscountryrequiredindicatorrequired

country_profile

Country Profile

Get a snapshot of a country's key macro indicators (latest available values): GDP, GDP per capita, GDP growth, inflation, unemployment, and population. Country accepts an ISO code.

Parameterscountryrequired

compare_countries

Compare Countries

Compare one indicator across several countries (latest available value each). Good for ranking or benchmarking economies.

Parameterscountriesrequiredindicatorrequired

us_series

US Series

Get a key US economic time series. From the Bureau of Labor Statistics: us_unemployment_rate, us_cpi, us_nonfarm_payrolls, us_labor_participation, us_avg_hourly_earnings, us_ppi. From the US Census Bureau: us_retail_sales (advance retail & food services, seasonally adjusted). The BLS series are kept warm by Datakoot and always available. A raw BLS series ID is also accepted, but BLS rate-limits by client IP and Datakoot runs on shared edge IPs, so an uncached series may return an upstream-limit error instead of data; that error means the upstream refused, not that the series does not exist.

Parametersseriesrequired

list_indicators

List Indicators

List the indicators this server supports (World Bank + US BLS), with descriptions. Call this to discover what you can query.

Takes no parameters.

Version history

1
  1. v2.1.0LatestSep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Datakoot integrations