MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
@traseq/agentgithub.com/traseq/agentupdated this year
Traseq MCP server, CLI, and SDK for AI-assisted trading strategy research, SignalGraph authoring, validation, backtesting workflows, and system template composition.
npm MIT -
honest-backtest-mcpupdated this year
MCP server for the Honest Backtest API — backtest trading strategies and get told why the results may not mean what they appear to mean
npm MIT -
QuantDinger is an open-source AI trading platform for quantitative trading across crypto, stocks, and forex. Run strategy backtests, paper trading, and live execution with multi-agent research in a self-hosted stack that includes API access, MCP tools, and optional monitoring.
Apache-2.0 ★ 9 -
Describe a trading strategy to your AI agent in plain English, get a full backtest with monthly drawdowns and an HTML tearsheet. Robinhood Trading MCP + yfinance fallback.
MIT -
TextToQuant MCP server: backtest plain-English trading strategies on real market data
MIT -
mcp-strategy-research-dbgithub.com/locupleto/mcp-strategy-research-dbupdated this year
MCP server for strategy research database - analyze trading strategy backtest results with Claude Code
★ 1 -
Open-source MCP for trading: live pump.fun calls, paper trades graded after costs, backtests and your own strategies.
npm MIT ★ 9 -
Algorithmic trading platform: multi-timeframe strategy engine, risk manager, backtesting and broker execution through the Interactive Brokers API and Webull MCP.
★ 2 -
MCP server for market data, backtests, live strategies, and trading via Crush
npm MIT -
pyon-mcpgithub.com/k4l-el/pyon-mcpupdated this year
MCP server that lets AI agents drive the Pyon trading platform (api.pyon.io): research, strategy building, backtesting, diagnosis, and parameter optimization
npm MIT -
tradingview-mcpgithub.com/debarpan2000/tradingview-mcpupdated this year
Advanced AI Trading Intelligence Framework — MCP server with live market intelligence, trade analytics, strategy optimization, pattern recognition, walk-forward backtesting, and 73 technical analysis tools
pypi MIT -
ai-tradergithub.com/whchien/ai-traderupdated this year
Backtrader-powered backtesting framework for algorithmic trading, featuring 20+ strategies, multi-market support, CLI tools, and an integrated MCP server for professional traders.
pypi GPL-3.0 -
Cursor plugin: backtest plain-English trading strategies on real market data (TextToQuant MCP)
MIT -
backtest-auditoractive
Backtest Auditor: a red-team lint for trading strategies (static lookahead/bias lint, Deflated Sharpe, cost and stability audit), as a Python library and an MCP server.
pypi Apache-2.0 -
openfinclaw-cligithub.com/mirror29/openfinclaw-cliupdated this year
One-stop quant-trading AI agent — research · strategy · backtest · paper trade from one prompt. Works in Claude Code, Cursor, and 20+ AI agents via MCP. 60-second install with auto Skill registration.
npm ★ 24 -
Claude Code plugin: backtest plain-English trading strategies on real market data (TextToQuant MCP)
MIT -
Local MCP server, CLI and agent skills for OKX — market data, derivatives & news intelligence, account analysis, perpetual-swap trading and Python strategy backtesting for Claude Code, Codex and any MCP client. OKX MCP 服务器。
npm MIT ★ 1 -
MCP server exposing Freqtrade backtesting, hyperopt and market-data tools to Claude and other LLM clients, plus a LangGraph agent that generates and optimizes trading strategies
MIT ★ 10 -
Free multi-exchange platform for algorithmic crypto trading with AI agents. Build bots as visual node graphs, backtest and optimize them, run them on Bybit, Binance and more. Any MCP agent (Claude, ChatGPT, Cursor, Gemini CLI, local LLMs) can design strategies for you.
★ 1 -
Cubicle: anti-hallucination trading for AI agents. Reverse-engineer a strategy or a TradingView Pine script, compile it, backtest it on recorded bars of NQ, ES, YM, BTC, ETH, SOL. MCP server + zero-dependency SDK (npm, Python).
MIT ★ 1 -
StratEvogithub.com/neuzhou/stratevono update data
Quantitative trading: quotes, backtesting, screening, and genetic algorithm strategy evolution.
pypi -
Local Solana memecoin terminal: holder maps, LARP and rug checks, a Claude analyst, and read-only MCP for your AI agent. Paper-trade, backtest and forward-test strategies with honest results. Never holds a key. Not financial advice.
AGPL-3.0 ★ 1 -
Janoriumno update data
Backtest crypto trading strategies on Binance spot and futures history with Janorium (free).
npm -
Free remote MCP server: analyze nested multi-strategy portfolios and backtest trading rules on real price history. No API key.
-
MetaTrader 5 in a real Windows VM (Docker + QEMU/KVM), driven over REST + MCP: trade, pull bars with server-side TA, run Strategy Tester backtests and optimizations, compile MQL5, deploy EAs onto charts, read and write terminal files, and copy Telegram trade signals. Multi-broker, multi-account. No Wine bullshit.
WTFPL ★ 31 -
coreforge-trading-mcpactive
MCP server for CoreForge trading analytics: strategy signals, signal board, market regime, backtests, indicators, portfolio risk, options Greeks, catalyst classification, US gov-contract awards, token analytics and Base chain reads — pay-per-call via x402
npm MIT -
MCP server + NinjaTrader 8 AddOn that gives an AI coding assistant eyes and a build loop for NinjaScript: compile with structured errors, chart and Print reads, headless backtests, walk-forward, lint, trade match vs research, screenshots. Opt-in Sim-only order and strategy control, plus Sim desk crash-recovery tools. Read-only by default.
MIT ★ 35 -
QuantContext is an MCP server that gives AI agents real quant computation for better trading: stock screening, strategy backtesting, and factor analysis.
pypi MIT ★ 10 -
The most complete open-source, self-hosted Agentic Trading OS—AI research, Python strategies, factor discovery, backtesting, optimization, paper/live multi-asset execution, risk controls, monitoring, MCP, and multi-tenant SaaS in one auditable stack.
go Apache-2.0 ★ 13,802 -
backtesting-mcpupdated this year
MCP server for backtesting platform - create strategies and run backtests locally via Claude Code
npm MIT -
Model Context Protocol (MCP) server for Pond3r DeFi yield strategy backtesting
npm MIT -
nsmbl-mcpgithub.com/nsmbl/nsmbl-mcpupdated this year
MCP server for NSMBL API - enables LLMs to create systematic investment strategies and run backtests
pypi MIT -
optopsy-mcpgithub.com/goldspanlabs/optopsy-mcpupdated this year
Rust-based rewrite of Optopsy: An options backtesting engine exposed via Model Context Protocol (MCP)
★ 26 -
Rust MCP server for MetaTrader 5 strategy work on macOS/Linux. Compiles MQL5 EAs, runs the Strategy Tester through Wine, stores deals in SQLite and exposes results to LLM clients.
MIT -
A quant research lab a desktop agent can drive over MCP: point-in-time backtesting with the caveat attached to every number
MIT ★ 1 -
Composer MCP Server - Backtest and Automate your trades with LLMs
pypi MIT License -
Market intelligence for your AI assistant - algo-trading strategies, analytics and specialized research knowledge.
pypi MIT -
tradeiq-lab-mcpactive
MCP server for backtesting Indian stock strategies with keyless Yahoo data: write a strategy, backtest it, export a report.
pypi Apache-2.0 -
Honest-by-construction AI strategy lab for crypto futures: describe a target, an agent writes the strategy, a Rust engine backtests it, and walk-forward plus a fenced holdout decide if it counts. macOS app + MCP server.
NOASSERTION -
@candleswarm/mcpactive
Secure CandleSwarm MCP server for AI agents to develop, backtest, and optimize crypto strategies with App-visible drafts.
npm MIT -
mcp-server-sentinelgithub.com/clarencyu-boop/mcp-server-sentinelupdated this year
MCP server for Sentinel Bot — algorithmic trading backtesting, bot management, and account operations via AI agents
npm MIT -
MCP connector for Strategy Arena Lab: let your AI backtest strategies on your own machine and get a verdict on sealed data.
MIT -
Strategy-agnostic Binance USDT-M futures backtest & execution engine — no-look-ahead, backtest/live parity, optional MCP server
pypi MIT -
alpha-forge-mcpgithub.com/alforge-labs/alpha-forge-mcpupdated this year
MCP server (stdio) exposing the AlphaForge forge CLI to Claude Code / Cursor / Codex (open-core wrapper, Apache-2.0)
pypi Apache-2.0 ★ 1 -
quantifyme-mcpgithub.com/malcolm1232/hftagentupdated this year
Claude MCP server for QuantifyMe — deploy trading strategies from natural language.
pypi MIT -
Backtesting and walk-forward validation for crypto strategies, built to tell you when a strategy doesn't work. Deflated Sharpe, purge gaps, reconciliation, MCP server.
Apache-2.0 ★ 2 -
algochains-library-mcpupdated this year
MCP server for Claude Desktop: natural-language market research and strategy backtesting with the AlgoChains library.
pypi MIT -
AI trading journal MCP server: Claude Code, Codex or any MCP agent logs trades from chart screenshots, checks them against your own strategy rules, imports MT5/TradingView, and shows R-based stats in a local dashboard.
npm MIT ★ 1 -
An open, auditable strategy language for the AI era: trading strategies as JSON that humans, AI agents and execution systems can all read, validate and agree on. Validator, CLI, Agent Skill and MCP server included.
Apache-2.0 ★ 1 -
MCP server for backtesting NIFTY and SENSEX options strategies on real 1-minute data, from ChatGPT, Claude or any MCP client
npm NOASSERTION ★ 1 -
TraderWAI Charts for Gemini CLI: live market charts, OHLC data and strategy backtests (read-only MCP)
CC-BY-4.0 -
MCP launcher for the Stochastly desktop app: strategy graphs, backtests and research diagnostics from Claude, Cursor or VS Code
MIT -
Personal quant research and trading system: market data ingestion, a strategy lab with robust validation (walk-forward, permutation tests), a strategy registry, and a daily risk-checked trading tick. Python, DuckDB, FastAPI, MCP, Angular.
NOASSERTION -
Comprehensive MCP server for TradingView Desktop: complete Pine Script lifecycle (create/save/version), full Strategy Tester extraction (every metric, every trade), chart and layout control, replay, alert/watchlist tools and DOM-driven UI automation over Chrome DevTools Protocol. No computer vision.
NOASSERTION ★ 10 -
nifty-mcpgithub.com/vishalmdi/nifty-mcpupdated this year
MCP server for NIFTY 50 stock and index data — query candles, run backtests, compare strategies. Hosted at https://vjaiswal-nifty-mcp.hf.space/mcp
pypi MIT -
A backtest auditor that refuses to lie to you. MCP server with 6 gates (data source, look-ahead, sample overlap, random baseline, portfolio simulation, multiple testing) that must catch planted errors before giving a verdict. 一个不肯对你撒谎的回测审计器 · Binance Agent OS Hackathon Track A
★ 1 -
Independent verifier for trading strategies written by AI agents and humans: catches look-ahead bias, hidden costs and overfitting. MCP server, CLI, GitHub Action, signed certificates.
pypi MIT ★ 10 -
Local-first MCP server for AI-assisted Backtrader strategy development: immutable datasets, private drafts, and bounded subprocess backtests via 30 typed tools. Offline & backtest-only.
MIT ★ 1 -
Windows app for stock and ETF monitoring, historical replay, paper trading, and guarded live trading through Robinhood, with scriptable strategies, local candle storage, and optional MCP automation.
MIT ★ 1 -
Systematic multi-strategy analysis engine for TradingView — 311 cited quant models, confidence scoring, risk-based position sizing, and verified Pine Script v6 export. Works on the free TradingView tier.
MIT ★ 1