Best MCP servers for backtesting

Updated October 2026 · Written by QuantGPT, one of the six servers below, so read it knowing that

// The short answer

An MCP server is how an AI assistant such as Claude or ChatGPT reaches an outside tool. For backtesting, two questions decide it: where does the backtest run, and on what data?

If you want your AI to test an idea on decades of US stock history without writing code, QuantGPT runs the backtest on its own servers and sends back the numbers, losing years included. If you write code and want the same algorithm to go live, QuantConnect's hosted server drives its engine. BotSpot turns a plain-English idea into a Python bot for your broker. Panther tests indicator rules on crypto, forex, gold and silver, and Keel builds strategies for Hyperliquid perpetual futures. EODHD's server supplies global market data; its MCP pages describe no backtest tool.

Side by side
QuantGPT
EODHD
QuantConnect
BotSpot
Panther
Keel
Questions
How we compared

// Side by side

Facts about other servers come from their makers' own pages, checked 2026-10-27; each section below links its sources.
Server	Markets covered	History depth	What it does	AI clients	Price
QuantGPTthis site	US stocks and indexes; also crypto, commodities, FRED macro, prediction markets, sports odds and weather	US stocks and ETFs; S&P 500 index levels from 1928; single stocks thin before 1980; companies that later delisted in market-wide backtests from 1998 (98% of them), survivors only before	Runs backtests, parameter sweeps, screens and event studies on its own servers; read-only SQL over its warehouse; no order tools. On QuantGPT Pro, QuantGPT Cloud runs your own code at your own broker	claude.ai, Claude Desktop and ChatGPT over OAuth; Claude Code, Cursor, Gemini and any MCP client with a key	QuantGPT $49 a month or QuantGPT Pro $149 a month, each with a 3-day free trial, card up front; Business from $1,499 a month
EODHD MCPdata	70+ exchanges: stocks, ETFs, indices, forex, US options; fundamentals, news, macro, ESG (per its MCP page)	30+ years on paid plans; the past year on the free plan	72 read-only data tools; technical indicators and pivot levels computed server-side; no backtest tool described	Claude, Claude Code, ChatGPT, Cursor, Windsurf, custom MCP clients	Free: 20 API calls a day. Personal plans $19.99 to $99.99 a month
QuantConnect MCPhosted	Equities, indexes, forex, crypto, futures and options	US equities from 1998, tick to daily	45+ tools over its API: write and compile code, backtest, optimize, deploy live. Hosted by QuantConnect	Claude Code, Copilot, Cursor, Devin Desktop; its README adds claude.ai and Claude Desktop	Needs a paid agent node (A1-1, A4-8 or A16-32); no flat price listed
BotSpot MCPby Lumiwealth	What its listed brokers trade: Alpaca, Tradier, Tradovate, Kraken, Coinbase	Not published on its MCP pages	Plain English to a Python bot, hosted backtests, bot monitoring; trading and deployment tools on the direct connection	Claude, ChatGPT, Claude Code, Cursor, Codex, Gemini	Free to connect; paid plans $49 to $399 a month at list price
Panther MCPby PantherWatch	30+ assets: crypto pairs, forex pairs, gold and silver	Not published in its README	13 tools: plain-English indicator backtests, parameter optimization, portfolio backtests, share links	Claude Desktop, Claude Code, ChatGPT (Pro, Team, Enterprise), Gemini CLI, Cursor, Cline, VS Code Copilot	Free API key at sign-up; no prices in its README
Keel MCPHyperliquid	Hyperliquid perpetual futures	Real Hyperliquid history; its README's example backtests start 2024-08-15	29 tools: compose strategies, deterministic backtests with fees, funding and slippage; live trading runs in the Keel web app	Claude, ChatGPT, Claude Code, Cursor, Codex, Windsurf	Free: 50 backtests a week. $29 to $199 a month, plus a trading fee of 1 to 5 bps

// The six servers, one by one

QuantGPTterminal.quantgpt.co/mcp · this site

Best forAsking research questions of decades of US market history from Claude or ChatGPT, with the backtest computed on the server and the losing years shown.

QuantGPT is the data and trading platform for AI.

ConnectOne MCP URL, https://terminal.quantgpt.co/mcp (Streamable HTTP). claude.ai, Claude Desktop and ChatGPT sign in over OAuth with no key to paste; Claude Code, Cursor, Gemini CLI and other clients send a key from your account page. Guides: Claude, ChatGPT, Gemini, Cursor.
DoesThe backtest runs on QuantGPT's servers and the result comes back with the numbers behind it, losing years included. Tools cover rule backtests, parameter sweeps, screens, stock grades, event studies and read-only SQL across the warehouse.
Library175 documented strategies, 55 of them runnable in one call from your AI; the rest are read-only for now.
DataUS stocks and ETFs. Companies that later delisted are in the market-wide backtest universe from 1998 (12,521 of the 12,841 priced since then, 98%); before 1998 it holds survivors only, so a market-wide backtest that starts earlier leans toward survivors. Backtests start in 1998 unless you pick another year. Fundamentals are joined by filing date; about 9% of quarters carry an estimated filing date. Stock coverage is the US market.
Check itThe public verify page shows our daily bars one at a time, to hold against any independent source. No MCP tool trades: nothing your AI calls places, changes or cancels an order.
CloudOn QuantGPT Pro, QuantGPT Cloud runs your own code and sends its orders to your own brokerage account under your own keys (Alpaca today), using only the broker's own order types. QuantGPT never manages a trade. How QuantGPT Cloud works.

Plans: QuantGPT is $49 a month (200 backtests and 500 AI calls a day, 3 keys) and QuantGPT Pro is $149 a month (1,500 AI calls a day, 5 keys, QuantGPT Cloud), each with a 3-day free trial on the plan's full daily limits, card up front, cancel any time. Business is custom, from $1,499 a month, by call. Compare the plans or start your 3-day free trial.

Pick another server if you need listings outside the US.

EODHD MCPmcp.eodhd.com · market data

Best forLooking up global market data inside your AI: prices, fundamentals, news, options and macro, with a free tier to start.

Tools72 read-only tools in 15 categories, across 70+ exchanges, with 30+ years of history.
ConnectTwo endpoints: v1 takes an API key in the URL (its page names ChatGPT, Claude Code and custom agents) and v2 uses OAuth 2.1 (Claude Desktop).
DoesFetches data. Its docs list server-side technical indicators and support and resistance levels by five pivot methods; its MCP pages describe no backtest tool, so a backtest on its data is up to your AI or your own code.
PriceFree plan: 20 API calls a day and the past year of data. Personal-use plans run $19.99 to $99.99 a month with 30+ years of history; commercial use is priced separately. MCP tool calls use the same quota as regular API requests.

Sources, checked 2026-10-27: eodhd.com/lp/eodhd-mcp-server, eodhd.com MCP docs, eodhd.com/pricing. The longer version: QuantGPT vs the EODHD MCP server.

QuantConnect MCPquantconnect.com/api/v2/mcp · hosted

Best forDevelopers who want an AI to write, backtest and deploy full algorithms on QuantConnect's engine, across many asset classes.

Tools45+ tools covering the QuantConnect API: projects, files, compiling, research notebooks, backtests, parameter optimization and live trading. Hosted by QuantConnect, with nothing to install.
ConnectPoint an MCP client at the hosted endpoint and authorize it against your QuantConnect organization in the browser; its GitHub README calls this the preferred way. Its docs give guides for Claude Code, Copilot, Cursor and Devin Desktop, and the README also walks through claude.ai and Claude Desktop.
DataUS equities from 1998, tick to daily, a dataset QuantConnect's docs describe as survivorship-bias-free. The free plan's data list covers equities, indexes, forex, crypto, futures and options.
PriceThe Free plan lists unlimited backtesting but no API access. The hosted MCP server needs a paid agent node (A1-1, A4-8 or A16-32) in your organization; the free A-MICRO node cannot connect. Paid tiers are priced by the setup you choose.

Sources, checked 2026-10-27: quantconnect.com/mcp, MCP server docs, MCP key concepts, GitHub README, US Equities dataset, quantconnect.com/pricing.

BotSpot MCPmcp.botspot.trade/mcp · by Lumiwealth

Best forTurning a plain-English idea into a Python trading bot, backtesting it, and running it at your own broker.

ToolsIts README says the server lists its tools at connection time: strategy creation and revisions, hosted backtests, bot monitoring, broker snapshots and portfolio reports, plus trading and deployment actions on the direct connection. Strategies are Python on the open-source LumiBot library.
ConnectOAuth sign-in from Claude, ChatGPT, Claude Code, Cursor and Codex, with no API key to paste. Its site also names Gemini.
MarketsTrades run through your own broker; its homepage lists Alpaca, Tradier, Tradovate, Kraken and Coinbase. The history depth of its backtest data is not published on its MCP pages.
PriceFree to connect; paid plans unlock heavier backtests, live bots and real-money trades. Light, Starter, Pro and All Access list at $49, $99, $199 and $399 a month; on 2026-10-27 its pricing page showed Light and Starter at 50% off.

Sources, checked 2026-10-27: GitHub README, Lumibot docs: BotSpot MCP, botspot.trade, botspot.trade/pricing.

Panther MCPpanther.watch/mcp · by PantherWatch

Best forQuick plain-English backtests of indicator rules on crypto, forex, gold and silver.

Tools13 tools: list assets, fetch prices, run and poll backtests, optimize parameters, run weighted portfolio backtests, and get a shareable link to each result.
Markets30+ assets: 20 crypto pairs via Binance, 10 forex pairs via IC Markets, plus gold and silver. Its README lists no stocks.
Rules25 indicators, including SMA, EMA, RSI, MACD and Bollinger Bands; long, short or both directions.
ConnectThe remote endpoint, or locally with uvx panther-mcp and an API key. Clients in its README: Claude Desktop, Claude Code, ChatGPT (Pro, Team and Enterprise in developer mode), Gemini CLI, Cline, Cursor and VS Code Copilot. The key is free at sign-up; the README gives no prices and no history depth.

Source, checked 2026-10-27: GitHub README.

Keel MCPmcp.usekeel.io/mcp · Hyperliquid perps

Best forStrategies on Hyperliquid perpetual futures, where the same compiled strategy runs in the backtest and live.

Does29 tools to search 251 strategy building blocks, compose a strategy and run deterministic backtests on real Hyperliquid history with fees, funding and slippage. Its lab adds walk-forward and Monte Carlo calculators.
DataHyperliquid price bars and hourly carry; its README's example backtests run from 2024-08-15. Its pages publish no single start date.
ConnectA hosted endpoint, or a local command-line tool and server (pipx install keel-trade). Clients named: Claude, ChatGPT, Claude Code, Cursor, Codex and Windsurf. The hosted connector has no live-write tools: running a strategy with real capital happens in the Keel web app, and the local live tools stay off unless you opt in and arm them on your machine.
PriceFree: 50 backtests and 20 AI messages a week, 1 live strategy, and a 5 bps trading fee. Starter $29 (3 bps), Trader $79 (2 bps) and Pro $199 (1 bp) a month.

Sources, checked 2026-10-27: usekeel.io/keel-mcp, GitHub README, usekeel.io/pricing.

// Questions

What is the best MCP server for stock market backtesting?

It depends on who does the work. As of October 2026: if you want your AI to test a rule on decades of US stock history without writing code, QuantGPT runs the backtest on its own servers and sends back the numbers, losing years included; its market-wide backtests include companies that later delisted from 1998 on (98% of them), and survivors only before that. If you write code and want the same algorithm to trade live, QuantConnect's hosted MCP server drives its engine, with US equity data from 1998. BotSpot turns a plain-English idea into a Python bot that runs at your broker. Panther (crypto, forex, gold and silver) and Keel (Hyperliquid perpetual futures) serve other markets. EODHD's server supplies market data, and its MCP pages describe no backtest tool. QuantGPT publishes this page, so weigh that.

How do I connect Claude to real stock market data for backtesting?

Add an MCP server as a custom connector. In claude.ai or Claude Desktop, open Customize, then Connectors, click + and choose Add custom connector, paste the server's URL and sign in when Claude asks. For QuantGPT the URL is https://terminal.quantgpt.co/mcp and the sign-in needs no key; in Claude Code, run claude mcp add with a key from your QuantGPT account page. Then ask Claude to run a backtest and it calls the server's tools mid-conversation. EODHD's data server connects the same way; its page gives an OAuth endpoint for Claude Desktop and a key-based one for other clients. Step by step: quantgpt.co/learn/connect-claude.html.

Can AI assistants run real backtests on historical market data?

Yes, when the MCP server they connect to has a backtest engine: the AI sends the rules, the server computes them on its stored history, and the results come back into the chat. As of October 2026, QuantGPT, QuantConnect, BotSpot, Panther and Keel all describe backtest tools on their MCP servers. A data-only server returns rows, and the AI then has to do the math inside its own context window, on whatever fits. Either way a backtest is hypothetical: check the sample size, the losing years, the trading costs, and whether companies that later failed are in the data.

How can I backtest a trading strategy with ChatGPT?

Connect ChatGPT to an MCP server that runs backtests, then describe the strategy in plain English. In ChatGPT, open Settings, then Security and login, and turn on Developer mode (OpenAI offers it on Plus, Pro, Business, Enterprise and Education accounts, on the web). Then go to chatgpt.com/plugins, select the plus button, name the app and enter the server's URL under Connection. For QuantGPT that is https://terminal.quantgpt.co/mcp, and you sign in to QuantGPT with no key to paste; on a Business, Enterprise or Education workspace an admin may need to allow developer mode first. Panther's README lists ChatGPT Pro, Team and Enterprise in developer mode, and BotSpot and Keel list ChatGPT too. Step by step: quantgpt.co/learn/connect-chatgpt. Without developer mode, QuantGPT's paste-pack gives ChatGPT the context in one block, but ChatGPT then cannot run the backtests itself.

// How we compared

QuantGPT publishes this page, and QuantGPT is one of the six servers in it. Every fact about another server comes from its maker's own public pages, GitHub README or docs, linked in its section, as read on 2026-10-27. We did not run the other servers or time them. Tool counts, data and prices change often, so check the linked page before you pay. Facts about QuantGPT come from its own plans, guides and product.

This is not every MCP server that touches markets. We picked servers whose makers publish enough to compare on markets, history, tools, clients and price. Where a maker does not publish a fact, the table says so rather than guess. If you build one of these servers and something here is wrong or out of date, write to desk@quantgpt.co and we will correct it.

Facts about other companies are from their public pages as of the date above and may have changed. EODHD, QuantConnect, BotSpot, Panther, Keel and every other product named here are trademarks of their owners; no affiliation or endorsement is implied. Backtests are hypothetical and gross of costs unless stated, and past results, real or simulated, do not predict future results. QuantGPT is research software, not investment advice, and never places a trade. The terms govern.