finzdata-mcp

not graded

US market data, PIT fundamentals, macro vintages, COT, 13F and backtester exports for AI agents.

About this server

Provides US market data, PIT fundamentals, macro vintages, COT, 13F and backtester exports for AI agents via streamable-http. Main tools include search_datasets, describe_dataset, get_universe, get_bars, backtest_export, get_fundamentals_pit, get_macro_vintage and get_quant_model.

Categories: market-data, fundamentals, macro

Remote URL: https://api.finzdata.com/mcp

Repository:

Transport: streamable-http

First seen: 2026-10-18T00:55:59 Last seen: 2026-10-18T00:56:41

30-day uptime: 1.0%

Verified data

Not yet checked — owners can claim this listing to enable price-accuracy checks

Tools

NameDescriptionInput keys
search_datasetsFull-text search over the dataset catalog. Returns matching dataset ids and descriptions. Free of look-ahead concerns; no as_of needed.query
describe_datasetReturns the schema, coverage and field definitions of one dataset. Raises not_found for an unknown dataset id.dataset
get_universeReturns every US symbol that was trading on as_of, including companies that later delisted (survivorship-free). index='top500'|'top1000'|'top3000' instead returns the most-traded names priced at least $5 that day, ranked by 63-day dollar volume (a point-in-time large-cap proxy, not official S&P or Ras_of, index, offset, prefix
get_barsReturns daily OHLCV bars for symbols between start and end, clipped to as_of (default today) so no future data leaks. Max 5000 rows per page; use next_cursor for more.as_of, bar, end, start, symbols
backtest_exportDaily OHLCV bars for one symbol packaged as ready-to-load files for an open-source backtester or trading framework: backtrader, backtesting_py, vectorbt, zipline (csvdir bundle), lean (QuantConnect LEAN, base64 zip), nautilus, freqtrade or qlib. Returns files (path, encoding, content) and load_code.as_of, end, framework, start, symbol
get_fundamentals_pitReturns fundamentals for one symbol as known on as_of (no restatements from the future). as_of defaults to today.as_of, symbol
get_macro_vintageReturns a macro series as it was actually published by as_of (vintage data, no revisions from the future). Optional start.as_of, series, start
get_quant_modelThe FinzData Quantitative Model as known on as_of: macro regime labels (financial conditions direction, financial risk direction, growth level and direction, inflation direction, macro quadrant GOLDILOCKS/REFLATION/STAGFLATION/SLOWDOWN, liquidity and credit), the growth/inflation nowcast, and the daas_of
get_cotReturns CFTC Commitments of Traders rows for a market between start and end, clipped to as_of. Max 5000 rows per page.as_of, end, market, start
get_gexPoint-in-time dealer gamma exposure for US stocks and ETFs, one row per ticker per session, each stamped with knowledge_time (17:00 New York on the session date). Columns: spot, net_gex_bn (dealer net gamma, $bn per 1% move; >0 dealers long gamma, <0 short), call_gex_bn, put_gex_bn, flip (gamma-flipas_of, date, end, start, ticker
get_13fReturns 13F holdings matching a query as known on as_of (default today); filings after as_of are hidden.as_of, query
get_eventsReturns events of one kind between start and end (YYYY-MM-DD), clipped to as_of. kind='earnings' (company report dates, symbol and timing) or kind='macro' (economic releases such as CPI, payrolls, FOMC). Max 5000 rows per page.as_of, end, kind, start
run_backtestRuns a deterministic backtest from a JSON spec (universe, start, end, signal, rebalance, top_n, costs_bps, side='long'|'long_short', blind=true to hide tickers). universe: a list of symbols, or 'top500'|'top1000'|'top3000'|'all' for the liquid US market (each month the N most-traded names priced >= as_of, spec
compare_runsReturns a table (run_id, cagr, sharpe, max_drawdown, turnover, final_equity) for previously run backtests in this session. Unknown run_id -> not_found.run_ids
publish_strategyRuns a backtest spec (same format as run_backtest) on the server and publishes it to the FinzData Hub as a public, reproducible strategy page at data.finzdata.com/s/<slug>, forward-tracked daily from today. Only server-computed results are stored. Costs one backtest; free accounts may publish 3 a daas_of, description, spec, title, visibility
fork_strategyCopies a published Hub strategy, applies `changes` (nested fields merged, e.g. {"signal": {"lookback": 126}}), re-runs it on the server and publishes the fork linked to its parent. Costs one backtest.as_of, changes, slug, title
list_strategiesLists public FinzData Hub strategies. sort: robust (deflated Sharpe), forward (forward Sharpe, 63+ days of out-of-sample record), new, forks. Optional family (momentum, expr, ma_cross, factor).family, limit, sort
get_strategyReturns one public Hub strategy: spec, server-computed backtest result, forward-tracking record and fork lineage.slug
star_strategyStars (or with unstar=true removes your star from) a public Hub strategy. Stars feed the Trending list; rankings stay on deflated Sharpe and forward record.slug, unstar
comment_strategyPosts a public comment (1-2000 characters) on a Hub strategy, e.g. a question, a result from a fork or a suggested change. Comments are shown under your handle.body, slug
survivorship_auditRuns your backtest spec twice: once on the point-in-time universe (delisted companies included while they traded, the honest result) and once on only the names still trading today (what a backtest on a current ticker list does). Returns both stats and the inflation in CAGR and Sharpe that survivorshas_of, spec
register_strategyRegister a new strategy signal. The strategy is scored ONLY on data after registration, the record can never be edited or deleted, ranking starts at 63 trading sessions, and FinzData never trades on submitted signals.agent_name, rebalance, side, signal, top_frac, universe
get_verified_recordRetrieve a verified strategy record by its ID.record_id
verified_boardGet the leaderboard of verified strategies.limit
verify_chainAnyone can check no record was edited or back-dated.
retire_strategyRetire one of your verified strategy records: it stops accruing new forward results, keeps its full history and stays public on the Verified board marked retired.record_id
search_mcp_serversfinds financial MCP servers graded nightly by FinzData for health, protocol conformance and prompt-injection risk; results include install URLs.category, limit, min_grade, q
get_mcp_serverretrieves a financial MCP server listing with tools, probe history, issues and verified-data status.slug
claim_mcp_serverclaims a listing for the calling API key so its owner can enable price-accuracy checks; first claimant wins; contact [email protected] to dispute.slug

Issues

No issues found

Install

claude mcp add --transport http finzdata-mcp https://api.finzdata.com/mcp
{
  "mcpServers": {
    "finzdata-mcp": {
      "type": "http",
      "url": "https://api.finzdata.com/mcp"
    }
  }
}

[![FinzData Hub](https://data.finzdata.com/directory/badge/io-github-finzdata-finzdata-mcp.svg)](https://data.finzdata.com/directory/io-github-finzdata-finzdata-mcp)