Economy Intel MCP Server — Datakoot

Economy Intel MCP provides macroeconomic data as Model Context Protocol (MCP) tools for AI agents. It exposes GDP, inflation, unemployment, and related trade and population figures, sourced from the World Bank (and US BLS referenced in the description), designed to be called mid-task without API keys. Tool access is limited to the server’s listed tools.

🛠️ Key Features

MCP server for macroeconomic data access
Country-level indicators over recent years (World Bank)
Country snapshot of key macro indicators (World Bank)
Cross-country ranking for one indicator (World Bank)
Tooling includes country_indicator, country_profile, compare_countries, and a us_series tool (partially shown)

🚀 Use Cases

Ground responses in real GDP, inflation, and unemployment figures
Compare macro indicators across multiple countries
Retrieve latest country snapshots for agent reasoning

⚡ Developer Benefits

No API keys required
MCP tool-based integration for mid-task data lookup
World Bank-backed indicator and profile retrieval

⚠️ Limitations

Tool list details are incomplete in the provided excerpt (e.g., us_series is not fully specified).

{ "type": "object", "properties": { "country": { "type": "string", "description": "Country as an ISO code or name, e.g. US, USA, or United States." }, "indicator": { "type": "string", "description": "World Bank indicator key: gdp, gdp_per_capita, gdp_growth, inflation, population, unemployment, life_expectancy, exports, imports, govt_debt_pct_gdp, real_interest_rate, fdi, co2_per_capita, internet_users. Call list_indicators for the full set. Raw World Bank codes are also accepted." }, "years": { "type": "integer", "default": 12, "description": "How many of the most recent years to return." } }, "required": [ "country", "indicator" ] }

{ "type": "object", "properties": { "country": { "type": "string", "description": "Country as an ISO code or name, e.g. US, USA, or United States." } }, "required": [ "country" ] }

{ "type": "object", "properties": { "countries": { "type": "array", "items": { "type": "string" }, "description": "Array of country codes or names to compare, e.g. [\"US\", \"DE\", \"JP\"]." }, "indicator": { "type": "string", "description": "World Bank indicator key: gdp, gdp_per_capita, gdp_growth, inflation, population, unemployment, life_expectancy, exports, imports, govt_debt_pct_gdp, real_interest_rate, fdi, co2_per_capita, internet_users. Call list_indicators for the full set. Raw World Bank codes are also accepted." } }, "required": [ "countries", "indicator" ] }

{ "type": "object", "properties": { "series": { "type": "string", "description": "One of the five warm BLS series: us_unemployment_rate, us_cpi, us_nonfarm_payrolls, us_labor_participation, us_avg_hourly_earnings. Those five are cached by Datakoot and always available. A raw BLS series ID is also accepted, but uncached series often hit BLS rate limits." } }, "required": [ "series" ] }

Tools

Tool

What it does

Source

country_indicator

An indicator (GDP, inflation, unemployment, population, ...) for a country over recent years

World Bank

country_profile

A snapshot of a country's key macro indicators, latest values

World Bank

compare_countries

Rank one indicator across several countries

World Bank

us_series

Key US time series: unemployment, CPI, nonfarm payrolls, participation, earnings

US BLS

list_indicators

Discover every indicator and series this server supports

—

No API keys required.

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:

code

python3 examples/datakoot_macro_agent.py cpi

Install

Tools (5)

country_indicatorcountry_profilecompare_countriesus_serieslist_indicators

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://economy.datakoot.com/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "economy-gdp-inflation-unemployment": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://economy.datakoot.com/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

Economy Intel MCP