{
  "markdown": "# Economy Intel MCP — by Datakoot\n\nMacroeconomic 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.\n\n## Tools\n\n| Tool | What it does | Source |\n|---|---|---|\n| `country_indicator` | An indicator (GDP, inflation, unemployment, population, ...) for a country over recent years | World Bank |\n| `country_profile` | A snapshot of a country's key macro indicators, latest values | World Bank |\n| `compare_countries` | Rank one indicator across several countries | World Bank |\n| `us_series` | Key US time series: unemployment, CPI, nonfarm payrolls, participation, earnings | US BLS |\n| `list_indicators` | Discover every indicator and series this server supports | — |\n\nNo API keys required.\n\n## Quick start\n\n```\nclaude mcp add --transport http economy-intel https://economy.datakoot.com/mcp\n```\n\nOr point any MCP client at `https://economy.datakoot.com/mcp`.\n\n## Grounded, verifiable forecasting\n\neconomy-intel is not just data in — it is meant to improve what an agent\nconcludes. To show that, [`examples/`](examples/) has a small, legible agent that\ncalls this server's `us_series` mid-task, projects the next macro print against\nthe market consensus with the arithmetic shown, and submits it to\n[Headline Arena](https://headlinearena.com) — a public arena where AI-agent\nforecasts are scored against reality and the calibration is checkable by anyone.\n\nThe live version runs the loop the arena's maintainer asked for: it wakes on the\ndata-release calendar, discovers the open macro challenges, grounds each one it\ncan in official US series, and posts a forecast with its reasoning — while\n**skipping the challenges it cannot honestly ground** (PPI, PMI, the FOMC rate —\nanything economy-intel does not serve) instead of guessing. Post on signal, not\non a clock.\n\nThe point is not a clever model. It is that the inputs are official (World Bank,\nUS BLS), the reasoning is transparent, and the record is public. Run the example\nyourself — no account, no cost:\n\n```\npython3 examples/datakoot_macro_agent.py cpi\n```\n\n## Data & attribution\n\nCountry data comes from the [World Bank Open Data](https://data.worldbank.org) API (CC-BY 4.0); US series come from the [US Bureau of Labor Statistics](https://www.bls.gov) public data API (US public domain). Informational only.\n\nPart of [Datakoot](https://datakoot.com) — keyless intelligence APIs for AI agents.\n",
  "bytes": 2464,
  "sha": "7b14bf22ccc36d899e064f39e24f964a2d0840a42bc31b2d2da96b9c216b96a2",
  "repo_slug": "selflabbs/economy-intel-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_selflabbs_economy_intel_mcp_a51737a3/readme"
}