We built a remote MCP server that gives Kimi agents point-in-time financial data with no look-ahead bias, and wanted to share it here for anyone building finance or research agents on Kimi.
Server: https://api.finzdata.com/mcp (Bearer API key or OAuth; free tier, no card)
Coverage: The whole market, remembered: every one of the 16,000+ US stocks that has traded on the NYSE and Nasdaq in the last 26+ years, delisted included, point in time. Around them: 139 futures markets with every contract since 2007, the VIX and Cboe volatility indexes with the VIX futures curve, options-market gamma for single stocks, ETFs and the major indexes, 231 ETFs, and crypto since 2015. Macro exactly as it was known: 18,000+ series including CPI, payrolls, wages, GDP and the Treasury yield curve, every vintage kept. Plus COT positioning since 1986. Bars at every resolution you backtest on: 1-minute, 5-minute, 15-minute, 30-minute, hourly and daily, with tick-level trades on the Institutional plan. In pandas with one line: pip install finzdata.
What the tools cover
- Daily and intraday bars for every US stock, delisted names included
- 139 futures markets, dealer gamma (GEX), CFTC COT positioning, 13F holdings
- SEC fundamentals as filed, and 18,000+ macro series exactly as first published
- Server-side backtests with a deflated-Sharpe overfitting check
Every data tool takes an as_of date, so an agent only sees what was public on that day.
Kimi CLI setup (~/.kimi/mcp.json, then kimi mcp test finzdata):
{
"mcpServers": {
"finzdata": {
"url": "https://api.finzdata.com/mcp",
"headers": {"Authorization": "Bearer YOUR_KEY"}
}
}
}
Full setup for Kimi and other clients: FinzData for AI Agents — Point-in-Time Data and Honest Backtests over MCP
If there is a Kimi MCP collection or examples page, we would be glad to be listed. Feedback on tool design for Kimi models is very welcome.