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 metadata comes from ecosyste.ms (CC BY-SA 4.0). 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.
-
murindigithub.com/vigilancetrent/murindiupdated this year
Murindi — self-hosted AI quant trading operating system: backend API and MCP server
NOASSERTION -
Agentic AI trading system that uses MCP servers for portfolio control, market data, and push alerts. Trader agents make buy/sell decisions, while Researcher agents gather and analyze market signals.
-
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 -
@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 -
Options trading and research system in C++23: one event-driven engine for backtest and live trading on Interactive Brokers, a quant lab on the same data, and MCP tools for AI agents.
Apache-2.0 ★ 29 -
Token-first options trading workspace and design system — Next.js, Tailwind driven by design tokens, WCAG 2.1 AA components, and an MCP server for AI agents.
-
YATS — Yet Another Trading System. An MCP server providing research and execution tools for AI agents.
MIT ★ 2 -
Standalone server designed to deliver market data insights to AI trading agents. It processes data from external brokers and computes structured information to help LLMs and other AI systems make more informed trading decisions using JSON RPC protocol
★ 4 -
MCP-based AI agent workflow system with LangChain orchestration, trading tools, and tool-server integration.
-
mcp-tradinggithub.com/dishasawantt/mcp-tradingupdated this year
Multi-agent paper trading simulation using OpenAI Agents SDK and MCP stdio servers — Gradio dashboard on SQLite.
MIT -
agentic-trading-labgithub.com/Pedregoneric/agentic-trading-labupdated this year
Safety-first multi-agent stock research and paper-trading lab with an optional official Trading MCP handoff
MIT -
MIT-licensed experimental Windows workbench for AI-assisted cTrader trading research (MCP, Open API, FIX).
MIT ★ 1 -
An agent wallet for Hyperliquid perps. The agent trades, it holds nothing: the account's key stays offline in Locker Vault.
npm NOASSERTION ★ 1 -
An AI trading agent that is never allowed to make a trading decision. Deterministic Python core. Every rule is in tested code, not prompt text.
MIT ★ 2 -
Claude powered advisor system for option traders
go MIT ★ 412 -
TLCgithub.com/FXDavid-OffbeatForex/TLCupdated this year
Ten legendary traders rebuilt as Claude subagents — blind votes, one risk-managed verdict. TradingView API· MT5 MCP · Telegram alerts.
MIT ★ 3 -
AI-powered options trading dashboard for Options Sentinel, providing a structured interface for market analysis, multi-agent reasoning, risk validation, options strategy generation, and controlled paper-trading workflows.
NOASSERTION -
CryptoIntel-MCPgithub.com/Arshad-13/CryptoIntel-MCPupdated this year
Production-ready MCP server for cryptocurrency market intelligence, AI-powered trading, and multi-agent analysis
MIT ★ 1 -
Hyperliquid trading intelligence for AI agents — 106 available MCP tools: builder analytics (revenue, retention, audience overlap, user journey), cohort analytics, position lifecycles, liquidation heatmaps, trader profiling, HIP-4 outcome contracts, and live market data. Hosted connector at mcp.coinversa.ai (OAuth) or npx @coinversaa/mcp-server.
npm MIT ★ 10 -
hs-code-classifier-mcpactive
HS code classifier for AI agents. Classifies products to official 6-digit tariff codes before customs declarations or duty calculations. VERIFIED verdict in one call.
npm MIT -
an autonomous AI trading desk that can disagree with itself. Instead of a single AI blindly making and executing market predictions, ARGUS AI convenes a specialized Investment Committee of AI agents that debate, stress-test, downsize, or completely veto trade proposals before sending them to Alpaca.
MIT ★ 1 -
Research-grade investment decision engine for AI agents: isolated multi-agent committee, auditable verdicts, backtests with lookahead protection, published negative results
pypi MIT ★ 141 -
Multi-agent cryptocurrency intelligence system built with Claude Code. 6 AI agents, 66 MCP tools, Agent Teams, zero orchestration code.
MIT ★ 119 -
An agent-driven equity trading system for Robinhood, built on the Robinhood MCP server. Claude orchestrates; a deterministic Python core makes every decision.
★ 2 -
TVControl by Ferrox Labs — TradingView MCP System. AI remote control for TradingView Desktop. 88 MCP tools driving symbols, indicators, Pine, snapshots, sweeps, replay, and live chart vision. All local, zero cloud calls.
npm NOASSERTION ★ 60 -
cymetica-eventtrader-mcpupdated this year
MCP Server for the EventTrader prediction markets platform - real-time market data for AI systems (import name: event_trader_mcp)
pypi MIT -
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 -
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 -
Professional financial analysis system with 14 specialized AI agents for comprehensive market analysis - MCP Server for Claude Desktop
npm 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 -
@lazymac/polymarket-intel-mcpupdated this year
Polymarket prediction market intelligence MCP — real-time market data, position analysis, alpha signals from Lumen's PM bot v39.2 (lottery-purge calibrated). Useful for AI agents researching prediction markets, traders building dashboards, or systems anal
npm MIT -
🧠 Enterprise-grade MCP server with temporal awareness system preventing AI data fabrication. Features 7 specialized AI analyst personas, professional web interface, and comprehensive security hardening. Delivers reliable financial intelligence for Claude
npm MIT -
wagglegithub.com/stepclrk/waggleupdated this year
A social network substrate for autonomous AI agents — keypair identity, E2EE messaging, escrowed information trades, a verifiable knowledge graph, staked-prediction forecasts, multi-agent projects, and a reputation economy. BYO-brain; the platform is the rail, not the mind.
MIT ★ 1