原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

FinzData market data

作者:finzdata版本 1.0.0i★ 0i在云端运行
注册名称io.github.FinzData/finzdata-mcp

安装方法

What it does

US stocks incl. delisted, futures, CPI/macro vintages, point-in-time GEX, 13F, COT, backtests.

  • Connects 在云端运行
  • Account or key Works without a key · add X-API-Key if you have one (often raises limits)
  • Category 会计、财务与税务

安装

选择你使用的 AI 应用,然后复制设置。

通过 5/5 项检查 · 你的提问会经过开发者的服务器(api.finzdata.com) · ✓ 命令已检查 2026年11月13日

第一步:你用哪个 AI?

选择你用的应用,步骤会显示在下方。

可连接 Claude · 约 2 分钟

不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加

  1. 打开 Claude 的 Connectors 页面

    CustomizeConnectors

    CustomizeConnectors1Add2https://…3Add4
  2. 点击“Add” → “Custom” → “Web”,填写这 2 项

    把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue

    Name · 名称FinzData market data
    Remote MCP server URL · 地址https://api.finzdata.com/mcp

    在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add

  3. 在聊天中开启

    +ConnectorsFinzData market data

  4. 试一试

    用 FinzData market data 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude 说正在使用 FinzData market data,或回答中出现 FinzData market data 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

能否连接 ChatGPT 取决于方案

完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页

  1. 在网页版 ChatGPT 打开添加 MCP 的页面

    Plugins+Add custom MCP server

    ChatGPTPlugins1+2https://…3Create4
  2. 填写名称和地址

    输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin

    Name · 名称FinzData market data
    Connection · 地址https://api.finzdata.com/mcp
  3. 在聊天中选择 FinzData market data

    开启新聊天,输入前先从插件列表中选择 FinzData market data

  4. 试一试

    用 FinzData market data 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 ChatGPT 说正在使用 FinzData market data,或回答中出现 FinzData market data 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Claude Code · 约 2 分钟

不需要密钥,不用安装程序

  1. 打开终端

    Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell

  2. 粘贴这条命令并按 Enter

    claude mcp add --transport http --scope user finzdata https://api.finzdata.com/mcp
  3. 在 Claude Code 中输入 /mcp

    应能看到 FinzData market data 在列表中并显示已连接

  4. 试一试

    用 FinzData market data 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude Code 说正在使用 FinzData market data,或回答中出现 FinzData market data 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Cursor · 约 2 分钟

不需要密钥,不用安装程序

  1. 点击这个按钮打开 Cursor

    在 Cursor 中打开

    Cursor 会请你确认安装,点击 Install

  2. 在 Cursor 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 FinzData market data 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Cursor 说正在使用 FinzData market data,或回答中出现 FinzData market data 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同

可连接 VS Code · 约 2 分钟

不需要密钥,不用安装程序

  1. 点击这个按钮打开 VS Code

    在 VS Code 中打开

    VS Code 会请你确认安装,点击 Install

  2. 在 VS Code 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 FinzData market data 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 VS Code 说正在使用 FinzData market data,或回答中出现 FinzData market data 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同

其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看

查看所有支持 MCP 的应用 →

通过网页连接的应用使用的地址

地址https://api.finzdata.com/mcp

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 FinzData market data 的人💬 讨论 →
开发者专用:终端命令和 JSON 设置

通过网页连接

Claude Code

claude mcp add --transport http --scope user finzdata https://api.finzdata.com/mcp

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "finzdata": {
      "url": "https://api.finzdata.com/mcp"
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "finzdata": {
      "type": "http",
      "url": "https://api.finzdata.com/mcp"
    }
  }
}

需要你填写的值

  • X-API-Key 机密 HTTP header
    Free key from https://finzdata.com/signup

说明仍为英文原文。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

一览

每周下载量i
不在 npm/PyPI 上
连接方式
在云端运行
传输方式
streamable-http
最新版本i
1.0.0
发布到注册中心i
2026年10月20日
代码最后更新i
2026年11月11日
作者
finzdata
注册状态
活跃

哪些应用可以使用它

依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。

通过互联网连接,适用于

ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast

全部应用及其优缺点 →

它能做什么

工具名称和描述与服务器在 2026年11月12日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。

  • search_datasets

    Answers 'which FinzData dataset holds this data?' Give a search phrase such as 'crude oil', 'insider trading' or 'housing'. Returns matching dataset ids, titles and descriptions. Use an id with describe_dataset, then call that dataset's tool (for example get_bars for prices, get_

  • describe_dataset

    Answers 'what fields and coverage does this dataset have?' Give a dataset id from search_datasets (for example prices_daily, cot, gex_daily). Returns the schema, coverage and field definitions. If the id is unknown, the error lists every valid id - call search_datasets to browse

  • get_universe

    Answers 'which US stocks were trading on this date - including ones that later delisted?' Give as_of (YYYY-MM-DD, defaults to today); optionally index top500/top1000/top3000 for the most-traded names priced at least $5 that day, prefix to filter, offset to page through 500 at a t

  • get_bars

    Answers 'what did these stocks do between these dates?' Give symbols (a list, or '/ES' for a futures root - plain 'ES' is the stock Eversource), start and end dates. Returns daily OHLCV bars clipped to as_of so no future data leaks; up to 5,000 rows per page, use next_cursor for

  • backtest_export

    Answers 'give me this stock's bars ready to load into my backtester.' Give a symbol and a framework (backtrader, backtesting_py, vectorbt, zipline, lean, nautilus, freqtrade or qlib); optionally start and end. Returns files (path, encoding, content) plus load_code - write each fi

  • get_fundamentals_pit

    Answers 'what were this company's fundamentals as known on this date - before later restatements?' Give a symbol and as_of (defaults to today). Returns SEC fundamentals as filed (earnings yield, book-to-market, ROE, leverage and more) exactly as known on that date. Covers US stoc

  • get_macro_vintage

    Answers 'what was inflation (or GDP, payrolls, retail sales) as first published on this date - not as later revised?' Give a series id (for example CPIAUCSL) and as_of; optionally start. Returns the series as actually published by as_of, with every vintage kept, across 22,700+ ma

  • get_quant_model

    Answers 'what macro regime are we in, and how stressed is the S&P 500?' Give as_of (defaults to today), or nothing for the latest reading. Returns the FinzData Quantitative Model labels as known on that date - financial-conditions and risk direction, growth level and direction, i

  • get_cot

    Answers 'how are traders positioned in this market?' Give a market (for example GOLD or CRUDE_OIL) and a start date; optionally end. Returns CFTC Commitments of Traders rows - managed money, producers, swap dealers, leveraged funds and asset managers, long/short/net - clipped to

  • get_gex

    Answers 'is dealer gamma long or short for this ticker - where are the gamma flip, call wall and put wall?' Give a ticker plus start/end for a time series, or a date alone for every name that session ranked by absolute net gamma. Returns one row per ticker per session: spot, net/

  • get_political_spending

    Answers 'who is spending election money, where, and on what?' Give a table (races, candidates, donor_geo, race_geo, flows, spending, vendors, state_local, state_local_geo); optionally cycle (2026, 2022 or 2018), state (2-letter code) and office (H or S). Returns cleaned, rolled-u

  • get_13f

    Answers 'who owns this stock, and what does this manager hold?' Give a query such as a manager name ('BERKSHIRE') or a ticker ('AAPL'). Returns 13F holdings as known on as_of (defaults to today); filings after as_of are hidden. Free keys get the last 12 months; full history with

  • get_events

    Answers 'when is this earnings report, or the next CPI / payrolls / FOMC release?' Give kind earnings or macro, plus start and end dates. Returns events clipped to as_of, up to 5,000 rows per page. kind=macro returns market-moving releases by default (CPI, payrolls, GDP, PCE, ret

  • run_backtest

    Answers 'would this strategy have worked - without look-ahead or survivorship bias?' Give a JSON spec (universe as a symbol list or top500/top1000/top3000/all, start, end, signal, rebalance D/W/M/Q, top_n, costs_bps, side long or long_short, blind=true to hide tickers). Signals:

  • run_strategy

    Answers 'how has this published strategy done since it started?' Give a slug from list_strategies; optionally end (default today). Returns stats, benchmark stats, equity curve, the published spec and the strategy page, re-running the strategy exactly as published on its full poin

  • compare_runs

    Answers 'which of my backtests performed best?' Give run_ids from earlier run_backtest calls in this session. Returns a table (run_id, CAGR, Sharpe, max drawdown, turnover, final equity) for each run. If a run_id is unknown, the error names it - call run_backtest again to get a f

  • publish_strategy

    Answers 'publish this backtest as a public, reproducible strategy page.' Give a spec (same format as run_backtest), a title (1-120 characters) and your hypothesis (what would falsify it); visibility public or private. Returns the new strategy's slug and page URL. Runs the backtes

  • fork_strategy

    Answers 'copy this published strategy and change one thing.' Give a slug and changes (nested fields merged, e.g. signal lookback 252 to 126); optionally a new title. Returns the fork's slug and page URL. Re-runs the strategy on the server and publishes the fork linked to its pare

  • list_strategies

    Answers 'what are the best published strategies on the FinzData Hub?' Optionally sort by benchmark (full record re-run nightly through today; strategies beating their benchmark on return and Sharpe first), robust (deflated Sharpe), forward (forward Sharpe, 63+ days out-of-sample)

  • get_strategy

    Answers 'show me this published strategy - its spec, backtest and forward record.' Give a slug from list_strategies. Returns the spec, server-computed backtest result, forward-tracking record and fork lineage, plus its public page URL. If the slug is unknown or the strategy is pr

  • star_strategy

    Answers 'star this strategy so it counts toward Trending.' Give a slug; pass unstar=true to remove your star. Returns the slug, star count and public page URL. Stars feed the Trending list; rankings stay on deflated Sharpe and forward record. If the slug is unknown or private, th

  • comment_strategy

    Answers 'ask a question or leave a note on this strategy.' Give a slug and a body (1-2000 characters) - a question, a result from a fork, or a suggested change. Returns the posted comment and the strategy's page URL. Posts a public comment under your handle. If the slug is unknow

  • survivorship_audit

    Answers 'how much of this backtest's return is survivorship bias?' Give a spec (same format as run_backtest, universe top500/top1000/top3000 or a symbol list). Returns both stats plus the inflation in CAGR and Sharpe that survivorship bias adds. Runs it twice - once on the point-

  • get_futures

    Answers 'give me every ES contract since 2007' (or any futures market's history). Give a root (ES, NQ, YM, RTY, CL, GC, SI, NG, ZN, ZB, VX, 6E and more; a leading '/' is fine) for the continuous back-adjusted series, or a contract (e.g. ESZ26) for one contract; optionally interva

  • get_futures_rolls

    Answers 'when does ES roll next - and what back-adjustment did the roll add?' Give a root (ES, CL, GC and more) or ALL for every market; optionally start and end. Returns the roll calendar for all 139 futures markets since 2007: for each front-month contract its first and last da

  • get_crypto

    Answers 'what did BTC (or ETH, SOL) do?' Give a symbol (pair, e.g. BTC-USD) and optionally interval (1min, 5min, 15min, 30min, 1hour or 1day, default 1day) plus start and end. Returns OHLCV bars clipped to as_of. Covers 512 crypto pairs (BTC-USD since 2013, ETH-USD since 2016, SO

  • get_fx

    Answers 'what did EURUSD (or USDJPY) do?' Give a symbol (currency pair, e.g. EURUSD) and optionally interval (1min, 5min, 15min, 30min, 1hour or 1day, default 1day) plus start and end. Returns OHLC bars, times in US Eastern, clipped to as_of. Covers 79 currency pairs (EURUSD, USD

  • get_index

    Answers 'what did the S&P 500 (or VIX) do?' Give a symbol (index, e.g. SPX, NDX, VIX, RUT, DXY) and optionally interval (1min, 5min, 15min, 30min, 1hour or 1day, default 1day) plus start and end. Returns OHLC bars, times in US Eastern, clipped to as_of. Covers 123 indexes: S&P 50

  • get_options_eod

    End-of-day US options chains since January 2010 for 5,800+ underlyings (stocks, ETFs and indexes, delisted included): every strike and expiry each day with last, bid, ask, bid and ask implied volatility, open interest, volume, delta, gamma, vega, theta and rho. Give symbol and da

  • get_ticks

    Answers 'show me every NVDA trade on this day.' Give a symbol and a day (YYYY-MM-DD); optionally start/end times (HH:MM, US Eastern) to narrow the window, or omit day to list the days available. Returns every trade print (time in UTC nanoseconds and ISO, price, size, exchange, co

  • get_global_pulse

    Answers 'how busy is the Suez Canal (or Singapore port, or US airspace) right now?' Give a dataset (chokepoints, ports, port_calls, air, air_europe, air_us or road); optionally match to filter by name or id (e.g. Suez, Singapore, JFK) and dim for air data. Returns daily real-worl

  • translate_stockcharts_scan

    Answers 'turn my StockCharts scan into a FinzData backtest.' Give a StockCharts scan (e.g. '[type = stock] and [daily close > daily sma(50,daily close)] and [rsi(14) < 70]'). Returns the FinzData signal formula (expr), universe, notes and a ready-to-run backtest spec; clauses not

  • backtest_stockcharts_scan

    Answers 'backtest my StockCharts scan on real history.' Give a scan and a start date; optionally end, symbols (e.g. a ChartList) to restrict the universe, top_n (default 50) and rebalance (D/W/M/Q, default W). Each rebalance holds the stocks that pass the scan, equally weighted u

  • register_strategy

    Answers 'score my signal out-of-sample from today, with a record nobody can edit.' Give agent_name, a signal formula, universe (top500/top1000/top3000/all), rebalance (daily/weekly/monthly), side (long/long_short) and top_frac (0-0.5). The strategy is scored only on data after re

  • get_verified_record

    Answers 'show me this verified strategy's forward record.' Give a record_id from register_strategy or the verified_board. Returns the record: signal, universe, registration date and every forward result since. If the id is unknown, the error says so - call verified_board to brows

  • verified_board

    Answers 'which verified strategies are leading?' Optionally give limit (1-200, default 50). Returns the leaderboard of verified strategies, ranked on forward results scored only after registration. Use get_verified_record for one record's full detail.

  • verify_chain

    Answers 'prove no verified record was edited or back-dated.' Give nothing. Returns the hash chain over every verified record so anyone can check the record is intact. If the check fails, the result names the broken link - contact info@finzdata.com with the record id.

  • retire_strategy

    Answers 'stop forward-tracking one of my verified strategies.' Give the record_id you registered. Returns the retired record id. It stops accruing new forward results, keeps its full history and stays public on the Verified board marked retired. If the id is unknown or is not you

  • search_mcp_servers

    Answers 'which financial MCP servers can I connect to - and which are healthy?' Give a search phrase q, optionally a category, a minimum grade (A-F) and a limit (1-50, default 10). Returns servers graded nightly by FinzData for health, protocol conformance and prompt-injection ri

  • get_mcp_server

    Answers 'show me this MCP server's listing, tools and probe history.' Give a slug from search_mcp_servers. Returns the listing with tools, probe history, issues and verified-data status, plus its directory page URL. If the slug is unknown, the error says so - call search_mcp_serv

  • claim_mcp_server

    Answers 'claim this directory listing so I can enable price-accuracy checks for it.' Give the slug of the listing you own; first claimant wins. Returns the claimed slug. If it is already claimed or the slug is unknown, the error says so - contact info@finzdata.com to dispute a cl

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月14日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 FinzData-com 验证,该账户拥有此仓库

  • ✓ 通过

    仍在维护

    代码最后更新于3天前

  • ✓ 通过

    有许可证

    使用 MIT

  • ✓ 通过

    端点有响应

    在 498 毫秒内响应(HTTP 200)

  • – 不适用

    使用 OAuth 登录

    无需登录

  • ✓ 通过

    工具描述中没有隐藏指令

    已读取 41 个工具描述,未发现针对 AI 的隐藏指令

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

使用 Google 登录后发帖

用户评价

还没有评价

用 Google 登录后写评价

与“会计、财务与税务”中的其他服务器比较i

  • 星标数多于此分类中其他 3239 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 3239 个服务器的 54% 更新
  • 基础检查结果等于或优于此分类中其他 3239 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

FinzData market data 安全吗?

它在 5 项适用的基础检查中通过了 5 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。

它还在维护吗?

GitHub 仓库最后更新于3天前,最新版本(1.0.0)于25天前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。

有什么可以替代它?

同一分类中有:CCXT, Finance Toolkit, AKQuant

同类别的其他选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

CCXT

Official CCXT MCP server - Market data and trading across 100+ exchanges and prediction markets

作者:ccxt广泛使用↓ 667/周★ 4.5万 整个仓库的星标2个月前更新

在你的电脑上运行

Finance Toolkit

500+ transparent financial methods calculated from raw statements, not third-party endpoints.

作者:JerBouma广泛使用↓ 1.6万/周★ 55235天前更新

电脑或云端

AKQuant

Write and backtest trading strategies with AKQuant: API lookup, strategy checks, backtest runs

作者:akfamily广泛使用↓ 3280/周★ 2604今天更新

在你的电脑上运行

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

FinzData MCP server

Research-grade US market data and server-side backtests for AI agents: Claude, ChatGPT, Gemini CLI, Cursor, Kimi, GLM and any MCP client.

Remote server: https://api.finzdata.com/mcp (Streamable HTTP, MCP 2026-07-28, accepts 2025-06-18 clients) Auth: OAuth 2.1 with PKCE (sign in with your FinzData API key), or the header Authorization: Bearer YOUR_API_KEY Free key: https://finzdata.com/signin · Pricing: https://finzdata.com/pricing · Agent docs: https://api.finzdata.com/agents.md

Coverage

Market data your backtests can trust. 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.

Why FinzData for agents

  • Survivorship-free. Universes include every company that traded on a date, delisted names included.
  • Point-in-time. Every data tool takes as_of, so answers contain only what was public that day: fundamentals as filed, and macro series as first published (ALFRED vintages).
  • Backtests run on the server. Describe a strategy and get back CAGR, volatility, Sharpe, drawdown, turnover, a benchmark, an equity curve, a reproducible run_id and a deflated Sharpe ratio that counts every variant you tried.

Tools (all read-only)

ToolWhat it returns
search_datasets / describe_datasetThe catalog, fields and coverage
get_universeEvery US symbol trading on a date, or the 500/1000/3000 most-traded
get_barsDaily and 1-minute OHLCV, split-adjusted
get_fundamentals_pitValuation and fundamentals as known on a date (P/E, EV/EBITDA, revenue, debt…)
get_macro_vintageFRED/ALFRED series exactly as published by a date
get_cotCFTC Commitments of Traders positioning
get_13fInstitutional holdings from 13F filings
get_eventsEarnings dates, splits and economic releases
run_backtestMomentum, MA cross, factor or formula strategies, long-only or long/short
compare_runsSeveral backtests side by side

Connect

Claude: add FinzData from the Claude connector directory, or add a custom connector with https://api.finzdata.com/mcp.

ChatGPT: add the FinzData app from the ChatGPT directory, or add a connector in developer mode with the URL above.

Gemini CLI:

export FINZDATA_API_KEY=your-key

gemini extensions install https://github.com/FinzData/finzdata-mcp

Cursor (.cursor/mcp.json), Windsurf, Cline, Kimi CLI, GLM / Z.ai coding tools and any client that takes a remote server:

{

"mcpServers": { "finzdata": { "url": "https://api.finzdata.com/mcp", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } }

Clients that only run local (stdio) servers: pip install finzdata-mcp (or uvx finzdata-mcp) with FINZDATA_API_KEY set. See README.pypi.md.

Example prompts

  • "Backtest 12-1 momentum on the 500 most-traded US stocks since 2010, monthly, top 50, 10 bps costs."
  • "What was the US unemployment rate for March 2020 as first reported?"
  • "How are managed-money traders positioned in gold futures?"
  • "Which institutions hold the most NVIDIA shares in the latest 13F quarter?"

Plans

Free accounts cover the last 12 months, with 100 data calls and 5 backtests a day. Paid plans and prepaid credits ($0.001 per data call, $0.05 per backtest) unlock full history.

Data, not investment advice. Support: info@finzdata.com · https://finzdata.com/support · Privacy: https://finzdata.com/privacy