StatCite serves official macro data — World Bank, IMF, ECB, and more — where every number ships with its full citation: source, dataset, series ID, canonical URL, license, and retrieval date. Plus verify_stat: check any claimed figure against the official series before it goes in your report.
AI agents write a growing share of the world's reports, briefs, and analysis — and they miscite numbers at measurable rates. StatCite exists so the number in your draft is the number in the official series, with the receipt attached.
One URL. No signup, no API key, no OAuth. Works in every major MCP client.
Settings → Connectors → Add custom connector → paste the URL. Works on all plans (Free allows one custom connector).
Name: StatCite URL: https://statcite.com/mcp
Settings → Apps & Connectors → enable Developer mode (paid plans) → create app with No Authentication. The server also implements the search/fetch pair required by deep-research connectors.
MCP server URL: https://statcite.com/mcp Authentication: No authentication
Add to ~/.cursor/mcp.json (or per-project .cursor/mcp.json):
{
"mcpServers": {
"statcite": { "url": "https://statcite.com/mcp" }
}
}
Add to .vscode/mcp.json:
{
"servers": {
"statcite": { "type": "http", "url": "https://statcite.com/mcp" }
}
}
One command:
claude mcp add --transport http statcite https://statcite.com/mcp
Any stdio-only client, via mcp-remote (use ≥ 0.1.16):
{
"mcpServers": {
"statcite": {
"command": "npx",
"args": ["-y", "mcp-remote@latest", "https://statcite.com/mcp"]
}
}
}
Plain HTTP for scripts, notebooks, spreadsheets, and Custom GPT Actions — OpenAPI spec:
curl "https://statcite.com/v1/indicator/inflation_cpi?country=BRB&latest_only=true" curl "https://statcite.com/v1/verify?indicator=inflation_cpi&country=USA&period=2023&value=4.1" curl "https://statcite.com/v1/fx?amount=100&from=USD&to=BBD"
An agent drafts “US inflation was 4.1% in 2023.” Before publishing, it calls verify_stat:
// tools/call → verify_stat {indicator:"inflation_cpi", country:"USA", period:"2023", claimed_value:4.1} { "verdict": "match", "claimed_value": 4.1, "official_value": 4.116338383, "explanation": "Claimed 4.1 vs official 4.1163 % (annual average) for 2023 — consistent (difference of 0.016 pp is within normal rounding).", "citation": { "source": "World Bank", "dataset": "World Development Indicators", "series_id": "FP.CPI.TOTL.ZG", "series_name": "Inflation, consumer prices (annual %)", "source_url": "https://data.worldbank.org/indicator/FP.CPI.TOTL.ZG?locations=USA", "license": "CC BY 4.0", "retrieved_at": "2026-07-25", "citation_text": "World Bank, World Development Indicators, series FP.CPI.TOTL.ZG (Inflation, consumer prices, annual %), data last updated 2026-07-13. Retrieved 2026-07-25 via StatCite." } }
Wrong year? Percent-vs-decimal slip? Billions-vs-millions? verify_stat diagnoses the classic errors and returns the correct, citable figure.
Available over MCP and mirrored as a REST API. All read-only.
Check a claimed figure against the official series → match / close / mismatch / cannot_verify, with diagnostics and the correct citation.
42 curated indicators — inflation, GDP growth, unemployment, government debt, current account, FDI… — for 200+ economies, with source fallback (World Bank → IMF WEO).
Headline economic picture of any country in one call: 11 indicators, each with its own citation. Built for country briefs.
“What is $100 (1995) worth in 2025 money?” CPI-ratio method with the exact index values and formula disclosed. Any country with CPI data.
ECB daily reference rates for ~30 majors since 1999, plus official annual-average rates for ~90 more currencies (BBD, XCD, JMD, KES…). Method always stated.
Raw access by explicit id: worldbank/…, fred/… (US monthly), dbnomics/IMF/WEO:latest/…. Transforms: YoY, % change, index rebase.
Free-text search over the curated registry plus DBnomics dataset discovery (IMF, OECD, Eurostat, BIS…).
Exactly which official sources power each answer, their licenses, and the attribution lines you're required to use.
The deep-research compatibility pair, so StatCite plugs into ChatGPT connectors and similar research pipelines out of the box.
StatCite is a citation layer over official statistics — never a black box. Data is fetched live from the sources and cached briefly for politeness.
| Source | Coverage | License |
|---|---|---|
| World Bank — World Development Indicators | ~1,400 annual indicators, 200+ economies, from 1960 | CC BY 4.0 |
| IMF — World Economic Outlook (via DBnomics) | Growth, fiscal & external indicators, 190+ economies, incl. projections | Free reuse with attribution |
| European Central Bank (via Frankfurter) | Daily euro reference FX rates, ~30 currencies, since 1999 | Attribution; informational rates |
| FRED — St. Louis Fed (optional) | US monthly/quarterly series (CPI, unemployment, fed funds, payrolls…) | FRED API terms |
| DBnomics (aggregator) | 90+ official providers (OECD, Eurostat, BIS, national offices) | Per provider |
Free while the agent economy grows up. Infrastructure costs are near zero by design; when paid tiers arrive, the free tier stays.
Yes — the service runs on near-zero-cost infrastructure and free official data APIs, so a generous free tier is sustainable. The long-term plan is boring and honest: keep the free tier, add paid convenience (keys, volume, bulk) for heavy users. No ads, no data resale.
StatCite adds no numbers of its own — it relays the official series and tells you exactly which one, fetched live and cached briefly. Macro data gets revised; every response notes that the value is the source's currently published figure. Computed transforms (YoY, inflation adjustment, FX bridging) disclose their formula and inputs.
The underlying licenses (CC BY 4.0 for the World Bank, IMF terms, ECB attribution) permit reuse — including commercial — with attribution. Every response includes the exact attribution line, which is precisely the point of StatCite.
A professional economist and data analyst who got tired of AI drafts with unverifiable numbers. The indicator registry, source fallbacks, and verification thresholds are economist-curated — e.g. government debt defaults to IMF WEO general government gross debt, not the patchier central-government series.
Cite the original source (the citation object gives you everything). Mentioning “via StatCite” is appreciated but never required.
Fair use, no hard published limit. Responses are cache-friendly; identical queries are served from edge cache. If your use case needs guarantees, email hello@statcite.com.