Economy Intel MCP (Model Context Protocol)

The io.github.selflabbs/economy-intel-mcp server provides macroeconomic data for AI agents as MCP tools. It exposes economic indicators such as GDP, inflation, unemployment, and related trade figures, using sources including the World Bank and US BLS. The package is designed so agents can call tools mid-task, without API keys.

🛠️ Key Features

Tooling for macro indicators (e.g., GDP, inflation, unemployment)
Sources include World Bank and US BLS
No API keys

🚀 Use Cases

Ground agent answers in recent macroeconomic and country-level figures
Compare economic indicators across multiple countries
Retrieve a country snapshot of key macro indicators

⚡ Developer Benefits

MCP tool calls: country_indicator, country_profile, compare_countries
Indicator queries cover multiple metrics (GDP, inflation, unemployment, population, etc.)
compare_countries ranks one indicator across several countries

⚠️ Limitations

Tools list is partial in provided data; additional tools beyond the shown excerpt are not fully described.

{ "type": "object", "properties": { "country": { "type": "string" }, "indicator": { "type": "string" }, "years": { "type": "integer", "default": 12 } }, "required": [ "country", "indicator" ] }

{ "type": "object", "properties": { "countries": { "type": "array", "items": { "type": "string" } }, "indicator": { "type": "string" } }, "required": [ "countries", "indicator" ] }

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.selflabbs.com/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "economy-intel-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://economy.selflabbs.com/mcp"
      ]
    }
  }
}

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

Economy Intel MCP