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.
-
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 -
TypeScript MCP server exposing a quantitative trading research platform as 116 typed tools, with multi-tier access control built on the MCP SDK AuthInfo flow.
NOASSERTION -
MCP server exposing SharpeBench's luck-robust quantitative evaluation tools for trading agents, including deflated Sharpe, pass^k, process discipline, and risk analysis.
npm MIT OR Apache-2.0 -
Provider-neutral intelligence plane with REST, MCP, CLI, pi and experimental dsh adapters for quantitative trading analysis.
MIT -
Evidence-first, self-hosted quantitative research workbench with reproducible backtests, factor diagnostics, paper simulation, and grounded AI.
MIT ★ 1 -
mcp-servergithub.com/QuantTradingOS/mcp-serverupdated this year
MCP server exposing QuantTradingOS tools for AI/chatbot clients
-
A lightweight Python MCP server that fetches TradingView chart snapshots using Playwright for fast, secure, and customizable browser automation.
MIT ★ 18 -
Signed orders for AI trading agents. Agents sign every order with their identity and the account holder's mandate; brokers verify for free. Open protocol (RFC 9421, Ed25519) and reference implementation.
Apache-2.0 -
ai-trader-for-mt5github.com/toki-plus/ai-trader-for-mt5updated this year
面向 MetaTrader 5 (MT5) 的 AI 交易助手与 EA 工程化框架。AI trading assistant and EA engineering framework for MT5, built with Python, MQL5, MCP tools, LLM agents, and risk modules.
★ 7 -
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 -
emquant-docs-mcpgithub.com/erwanjun/emquant-docs-mcpupdated this year
MCP server for EMQuant (东方财富量化终端) documentation - provides search, query and browse tools for Python & C# SDK docs
npm MIT -
stockhub-mcpgithub.com/timwu0101/stockhub-mcpupdated this year
StockHub MCP — 43-tool financial market data server for A-shares, HK stocks, US equities, funds, ETFs, futures, indices. Multi-source fallback: yfinance, efinance, Tencent, Sina, EastMoney, AkShare.
pypi MIT -
CRYPTYX MCP Server — the intelligence layer for digital assets, delivered via Model Context Protocol. 21 tools, 376 metrics, 8 factor classes, ~200 assets. Clarity in chaos.
npm MIT -
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 -
Supply chain digital twin simulation via 8 quantitative algorithms — connect any AI agent to live corporate, trade, sanctions, hazard, and financial data across 17 public data sources.
MIT ★ 1 -
QuantLab Pro is a quantitative ML research platform featuring six specialized agents, MCP-based tool integration, leakage-resistant time-series modeling, PyTorch experiments, backtesting, and reproducible MLOps tracking using Python, Streamlit, and SQLite.
MIT