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. 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.
-
Offline MCP server: an AI agent transpiles PineScript v6 → C++ and runs deterministic, TradingView-parity backtests locally (transpile, backtest, parameter grid, Binance OHLCV, Pine coverage lookup). One Docker container, no API key; code & data stay on your machine.
npm MIT ★ 9 -
Backtest any MT5 indicator through Claude AI — MCP server that reads real indicator signals and replays them on live broker data
MIT ★ 19 -
Free and source-available, self-hostable trading workspace: data, backtest, trading journal, news aggregator, rich-doc editor, portfolio, 20+ modules with a built-in MCP server and AI agent.
NOASSERTION ★ 86 -
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 -
bullarcgithub.com/bullarc/bullarcupdated this year
AI-powered technical analysis engine — 11 indicators, multi-source signal fusion, backtesting, paper trading, and MCP server for Claude. Written in Go.
MIT ★ 4 -
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.
★ 24 -
AI-powered trading research platform. Test any idea on stocks, futures, and crypto with event studies, backtesting, and statistical validation. MCP server with 8 tools. pip install varrd.
MIT ★ 25 -
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.
Apache-2.0 ★ 13,771 -
Is that trading record skill, or could it be luck? Check any Hyperliquid wallet, rescore leaderboards for best-of-N selection, and audit AI backtests for knowledge-cutoff leakage. Python stdlib, MCP server, agent skill.
pypi MIT -
Free, open-source charts for crypto, stocks and forex that your AI agent can drive. Indicators, drawing tools, scripts with strategy backtests, alerts, bar replay and multi-chart layouts, with an MCP server for Claude Code, Codex, Cursor and Gemini CLI.
MIT ★ 9 -
Stock research toolkit for AI agents — 73 tools + 21 skills for analysis, screening & backtesting across A/HK/US/JP/KR/TW markets. Works with Pi Agent, Hermes, OpenClaw, DeepSeek Harness (dsh) and any MCP client.
MIT ★ 94 -
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 -
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 -
Desktop market-analysis workbench you drive by talking to an AI agent. A local Python sidecar does the work - indicators, candlestick and chart patterns, walk-forward backtests, volatility/regime forecasts, DeFi P&L - as 59 MCP tools; an Electron viewer draws it live. Read-only research and labeled advice: no broker, no orders.
MIT ★ 2 -
Remote MCP server for AI agents: point-in-time market data, no look-ahead. 16,000+ US stocks incl. delisted, 5,100+ ETFs, ticks, 139 futures markets, options gamma (GEX) and chains, crypto, FX, indexes, COT, 13F, SEC fundamentals, 22,700+ macro vintages, congressional trades, election spending, Global Macro Pulse, server-side backtests.
MIT -
Free investment and retirement calculators for Claude and any MCP AI chat, plus compound interest, CD and high-yield savings, S&P 500, stock return, DCA, net worth and risk, with charts. No sign-in. And AI investing: turn an idea into rules, backtest, paper trade. Education only, not investment advice.
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 -
AI trading agents for US stocks with news backtesting that can't see the future: a public LLM trading agent leaderboard (rta-bench-1), frozen point-in-time 2020/2022/2026 markets (prices, VIX, news), a look-ahead check on every run, LLM agents over MCP, and paper/live trading on 10 brokers. 风险感知美股交易智能体 · 新闻回测 · LLM 榜单
pypi MIT ★ 141 -
sygnldata-agent-clientgithub.com/nhantour/sygnldata-agent-clientupdated this year
Pay-per-call market intelligence for AI trading agents — x402 (USDC on Base) + MCP. Market regime, execution costs, bar QC, backtest forensics.
-
A single-route FastAPI app that handles multiple AI tasks, includes optional JWT auth, integrates a minimal MCP server/client for tool calling, and ships with a basic trading backtest utility. Tested locally on macOS.
-
Research-grade investment decision engine for AI agents: isolated multi-agent committee, auditable verdicts, backtests with lookahead protection, published negative results
pypi MIT ★ 141 -
agentic-quant-studiogithub.com/wizard50/agentic-quant-studioupdated this year
Agentic Quant Studio — An intelligent workspace for building autonomous AI agents in quantitative finance. Research, code generation, backtesting, and RAG-powered knowledge — all in one studio.
MIT ★ 1 -
自托管中国基金组合分析与风险管理工具 — 自动净值更新 / 收益与回撤 / AI 投顾 / 定投回测 / 基金筛选 / 分红检测 | Self-hosted China fund portfolio analyzer: auto NAV sync, returns/risk analytics, AI advisor, DCA backtest, fund screener, dividend detection
MIT ★ 29 -
groww-mcpgithub.com/developerJai/groww-mcpupdated this year
🚀 The most complete MCP server for Groww — 25 tools, ⚡ automated TOTP auth, GTT/OCO smart orders, 📈 option chain with Greeks, backtesting. 🤖 Connect any AI assistant to your Groww trading account.
MIT ★ 4 -
FinzData MCP server: point-in-time market data for AI agents. US stocks incl. delisted, ETFs, ticks, futures, options gamma (GEX), crypto, FX, indexes, COT, 13F, fundamentals, 22,700+ macro series and backtests.
pypi MIT -
MCP server that gives AI agents quantitative risk analytics tools: Value at Risk (VaR) and Expected Shortfall by 4 methods, GARCH volatility forecasting, extreme value theory (EVT) tail risk, Basel backtesting, stress testing, and a credit-risk PD scorecard. Python, FastMCP, works with Claude.
MIT ★ 1 -
An Autonomous Hedge Fund AI Orchestrator by Corax CoLAB. Features Multi-Agent Consensus (Gemini, Claude, OpenAI), Proof-of-Brain logging, Telegram Command Center, and Agentic Backtesting. Integrates Edge AI with CCXT, Web3 data, and Freqtrade via a cyberpunk 3D dashboard.
MIT ★ 12 -
Fashion E-Commerce Intelligencegithub.com/alexgenovese/ecommerce-fashion-market-analysisno update data
# Fashion E-Commerce Intelligence MCP Server Empower your AI agents, copilots, and assistants with vertical domain-specific fashion intelligence. Built by [alexgenovese.com](https://alexgenovese.com), this Model Context Protocol (MCP) server provides automated **SEO auditing, category trend research, DTC demand forecasting, CRM segment enrichment, and campaign creative generation**—designed natively for Cursor, Claude Desktop, Claude Code, and any MCP-compatible environment. --- ## ⚡ What It Does | Capability | Without this server | With Fashion MCP | |---|---|---| | **SEO Auditing** | Manual checklists, generic advice | Automated **0-100 score** across 5 dimensions with fashion-specific validation (fit, material, color, season, schema, OG, Twitter Cards). | | **Trend Research** | Generic search queries | Deep category-level trend intelligence (trending keywords, colors, silhouettes, price tiers, market fit, confidence). | | **Demand Forecasting** | Spreadsheets & gut feel | Explainable weighted-rule forecast model: `baseline × trend × media × retention × inventory × seasonality` with backtesting. | | **CRM Segment Enrichment** | Static email lists | Customer segments enriched with trending colors/silhouettes/keywords, audience clusters, and ready-to-send targeted messaging. | | **Campaign Creative** | Standard copywriters per channel | Platform-specific campaign themes, hooks, value propositions, and ready-to-use creative briefs grounded in real-time trend data. | --- ## 🔧 Exposed Tools - `product_seo_audit`: Audit any fashion product listing for SEO best practices, structured schema, meta tags, and fashion relevance (fit, size, material). - `fashion_trend_analysis`: Analyze fashion trend data mapped from search engine and social media queries. *(Receives search data input seamlessly, no API key required)*. - `fashion_category_demand_outlook`: Get a rapid, light demand pulse check for a specific product category in a target market and season. - `fashion_dtc_forecast_analysis`: Generate complete DTC demand forecasts with scenario planning (base/upside/downside) and stock-out/overstock risk analysis. - `fashion_customer_trend_enrichment`: Map trending keywords, colors, and silhouettes onto existing CRM customer segments for targeted email/SMS campaigns. - `fashion_campaign_theme_recommendation`: Recommend conversion-optimized ad campaign themes, hooks, and creative briefs for Meta, Google, TikTok, or Email. --- ## 🔐 Privacy & Technical Features - **No API Keys Required:** All analysis, SEO audits, demand forecasts, and CRM enrichment tools run locally with the data you supply. Upstream search data for `fashion_trend_analysis` uses your existing Tavily MCP server. - **Explainable Outputs:** Every tool returns explicit `assumptions[]`, `dataGaps[]`, and `confidence` scores, so your agent always understands the reasoning behind recommendations. - **Zero-Config Local Cache:** Uses a local SQLite persistence layer (`~/.fashion-mcp/store.db`) to cache snapshots, feature stores, and forecast actuals for backtesting. ## 💻 Local Installation To install this stdio-based server locally via Smithery: ```bash npx smithery install alexgenovese/ecommerce-fashion-market-analysis ```
smithery -
Model Context Protocol server for backtest-kit: lets an LLM agent observe the live trading portfolio and open or close positions through guarded tools
npm 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 -
MCP server that catches fake backtests before you trust them: deflated Sharpe ratio, backtest overfitting (CSCV/PBO), data-snooping tests (White's Reality Check, Hansen's SPA), lookahead checks and pipeline placebos. 20 tools for Claude, Cursor and any MCP client; on npm, the MCP Registry and hosted at canlicapital.com/mcp.
MIT ★ 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.
MIT ★ 10 -
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.
MIT ★ 1 -
Composer MCP Server - Backtest and Automate your trades with LLMs
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 -
indexone-mcpgithub.com/index1one/indexone-mcpupdated this year
Remote MCP server for Index One: query financial index data, run backtests, and deploy systematic investment strategies from any MCP client.
MIT -
Stock market MCP server for Yahoo Finance data, technical analysis, portfolio tracking, and Python backtesting. Runs locally with no API key for core tools.
MIT ★ 728 -
MCP server and LangGraph tools for WorldQuant BRAIN alpha research. Backtest Fast Expression alphas, read results and browse data fields from Claude Code, Cursor or your own agent. Unofficial, not affiliated with WorldQuant.
MIT ★ 2 -
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。
MIT ★ 1 -
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 -
AIQuantificationToolsgithub.com/wqjuser/AIQuantificationToolsupdated this year
面向个人研究者的可审计量化研究工作台:行情筛选、AI 选股、策略回测、AI 评审与只读 MCP 接入。
★ 2 -
MCP server of skforecast-ai: deterministic time series forecasting as tools for coding agents.
pypi Apache-2.0 -
Inspect time series, forecast with your models, compare forecasts, and review observed outcomes.
Apache-2.0 ★ 1 -
High-performance quantitative trading framework based on Rust and Python
pypi MIT License -
Paper trading simulator for Polymarket
MIT ★ 508 -
Market intelligence for your AI assistant - algo-trading strategies, analytics and specialized research knowledge.
pypi MIT -
rozkoduj-mcpgithub.com/rozkoduj/rozkoduj-mcpupdated this year
Market intelligence for your AI assistant - algo-trading strategies, analytics and specialized research knowledge.
pypi MIT -
Trend0x MCP server: AI trading terminal for crypto and stocks (remote, streamable HTTP)
MIT -
@openfinclaw/cligithub.com/mirror29/openfinclaw-cliupdated this year
One-stop quant-trading AI agent for any coding assistant — MCP server + CLI
npm MIT -
Lightweight, self-hosted stock portfolio watcher and technical analysis workbench with Model Context Protocol (MCP) AI integration.
NOASSERTION -
A trading journal that proves which rules make you money. Tests rules on trades they never saw. Never places orders.
MIT -
Institutional Quantitative Trading & AI Platform: Microsoft Qlib (Alpha158 + LightGBM), MetaTrader 5 EA Bridge, Bloomberg Feed & FastMCP Agent. Live Demo: https://quantvibeapp.com
MIT ★ 3 -
Connect ChatGPT, Claude, Codex and other AI agents to your broker. Review accounts and positions, request trades for approval. Free to connect with BotSpot sign-in.
NOASSERTION -
63 deterministic quant computation tools for autonomous financial agents. Options, derivatives, risk, portfolio, statistics, crypto/DeFi, macro/FX, TVM. 1,000 free calls/day — no signup.
MIT ★ 14 -
A simulated stock market for testing trading strategies and AI agents. Orders move prices, any market can be forked, and every run reproduces exactly.
Apache-2.0 -
Kalshi and Polymarket historical order book data for AI agents: 118B+ rows, every book change, trades and settlements, including 15-minute Bitcoin markets.
MIT ★ 1 -
Re-run the work, recompute the number, block the wrong one before it ships — a deterministic guardrail for AI-computed results. CLI · Claude Code hook · MCP.
MIT -
美股进攻/防守四档信号系统:AI供需+货币/财政/行政四维数据驱动,公开Track Record,开放API/MCP · US stock attack/defense signal system: 4 data-driven dimensions, public track record, open API & MCP
★ 1 -
tradingview-indicator-search-mcp-servergithub.com/daviddme/tradingview-indicator-search-mcp-serverupdated this year
TradingView MCP server: search indicators and strategies, fetch Pine Script source. Works with Claude Code, Claude Desktop and Cursor. No API key needed.
MIT ★ 139 -
Python time series forecasting assistant built on skforecast: deterministic decisions, the script that ran, an optional LLM that explains them, and an MCP server for AI agents.
Apache-2.0 ★ 52