# Vibe-Trading

A local finance research agent with 74 MCP tools, nine backtest engines and 14 brokers.

*https://stockmarketstack.com/tools/vibe-trading · Financial MCP Servers & AI Agents*

## Facts

### At a glance

| Field | Value |
| --- | --- |
| Vendor | HKUDS |
| Category | Financial MCP Servers & AI Agents |
| Job | infrastructure |
| Website | https://vibetrading.wiki |
| Pricing model | open-source |
| Free tier | true |
| Open source | true |
| Licence | MIT |
| Self-hosted | true |
| Tested hands-on | false |
| Last updated | 2026-09-13 |

### Coverage

| Field | Value |
| --- | --- |
| Asset classes | stocks, etf, options, futures, forex, crypto, indices |
| Markets | us, ca, uk, asia |
| Works outside the US | true |
| Data latency | delayed |
| Platforms | web, cli, library |
| AI features | recommendations |

### Interfaces

| Field | Value |
| --- | --- |
| API | true |
| Webhooks | false |
| Scripting | Python |
| Python | true |
| Spreadsheet add-in | false |
| MCP server | true |
| Export | csv, json, pdf |

### Capabilities

Yes: screening, backtesting, automation, live_trading, paper_trading, portfolio_tracking, broker_import, news, options_analysis

No: charting, scanning, tax_reporting, alerts

*Verified: pricing 2026-09-13; capabilities 2026-09-13; coverage 2026-09-13.*

## What it is

Vibe-Trading is a finance research agent you install and run on your own machine, published by
HKUDS — the University of Hong Kong Data Intelligence Lab. `pip install vibe-trading-ai`, give it
one LLM provider key, and ask in plain language: it loads from 90 bundled skills, pulls bars from
whichever of its 27 data sources answers first, writes and runs strategy code, and returns a run
card with metrics and a tool trace. The same install ships a CLI, a FastAPI web UI, and an MCP
server exposing 74 tools over stdio or streamable HTTP — which is how most people attach it to an
agent they already use.

It is new. First commit 1 April 2026, v0.1.15 released 9 September 2026, last commit to `main` on
13 September 2026, MIT-licensed, not archived, roughly 33,300 stars. The star count runs a long way
ahead of the shipping record.

## Pricing

Nothing to buy: no hosted tier, no paid build, no data bundle. The cost is the model you point it
at, plus optional keys for premium data — including QVeris, a third-party credit-metered
marketplace the README links behind a referral code.

## Data & coverage

It ships loaders, not a feed. One `get_market_data` call fans out across 27 sources with a fallback
chain ordered by IP-ban risk, and most need no key. The loader layer is point-in-time historical
bars only — the project states that real-time ticks and order-book depth are out of scope and come
from broker connectors instead. Equities cover A-shares, Hong Kong, US, Canada, UK, India and
Korea; crypto via OKX, Binance and CCXT; forex via MetaTrader 5. Nine backtest engines plus a
cross-market composite and an options-portfolio engine sit behind them, with Monte Carlo
permutation, bootstrap Sharpe intervals and walk-forward validation.

## Integrations

Fourteen broker connectors, read-only or paper by default. Strategies export to TradingView Pine
Script, TDX, MQL5 and vn.py; sessions as Markdown or JSON; portfolio snapshots as CSV. It also
loads tools from external MCP servers, so it is a client as well as a server.

## Limitations

- No LLM of its own and no free inference. A weak model degrades it silently into answering from
  training data instead of running the tools.
- Live trading is the project's own "experimental and not verified by us against a real broker
  account". IBKR is read-only; Trading 212 refuses orders even on paper.
- The free data sources are public endpoints nobody promised to keep. A September 2026 fix
  documents eight years of requested history silently returning as two.
- The Electron desktop shell is built from source with Windows-only packaging; releases publish no
  installer.
- Version 0.1.x, five months old, and upgrades have broken once already — 0.1.10 moved to
  LangChain 1.x and needs a fresh virtualenv.
- It emits opinions on named securities: the shipped `investment_committee` preset ends in a "PM
  final call", which is a language model's view, not research you can audit.

## Alternatives

For read-only market data over MCP without an agent framework attached, single-purpose servers —
[SEC EDGAR MCP](https://stockmarketstack.com/tools/sec-edgar-mcp), or a data vendor's own MCP endpoint — are far less machinery. For backtesting
without an LLM in the loop, [NautilusTrader](https://stockmarketstack.com/tools/nautilus-trader), [QuantConnect](https://stockmarketstack.com/tools/quantconnect) LEAN and vectorbt do that job directly.
AI-Trader, from the same lab, is a hosted platform rather than a local workspace.

## FAQ

### What does Vibe-Trading cost to run?

The software is MIT-licensed and free, and market data for A-shares, HK, US, Canada, UK and crypto works with no key at all. The real bill is the LLM. Every run is tool-heavy, and the project's own guidance is that small or distilled models fabricate answers instead of calling tools, so plan on a mid-tier model — the shipped default is DeepSeek — or run Ollama locally for no cost but slower, weaker tool-calling.

### Can Vibe-Trading actually place a trade?

Yes, with guardrails, and the project calls it experimental and unverified against a real broker account. Live order placement exists for Robinhood, Tiger, Alpaca, OKX, Binance, Futu, eToro and MetaTrader 5, bounded by a mandate you commit — symbol allowlist, order size, exposure, leverage, daily cap — with a kill switch. Longbridge, Dhan, Shoonya and Zerodha are read plus paper only because they expose no runtime paper/live discriminator, IBKR is read-only, Trading 212 refuses orders even on paper, and order-placing tools are deliberately not exposed over MCP.

### Is Vibe-Trading the same project as AI-Trader?

No. Both come from HKUDS, but AI-Trader is a hosted agent-native trading platform — agents register on it to publish signals, copy trades and enter challenges — while Vibe-Trading is software you install and run yourself. They share an organisation, not a codebase.

### Does it need an OpenAI or Anthropic key?

Not specifically. It speaks to roughly twenty providers, including OpenRouter, DeepSeek, Gemini, Groq, Qwen, Zhipu, Moonshot and NVIDIA NIM, plus GitHub Copilot through an existing subscription and Ollama locally with no key. You supply one provider key; the choice is yours.

## Also worth comparing

- [MaverickMCP](https://stockmarketstack.com/tools/maverick-mcp.md) — Thirty-seven stock-analysis tools for any MCP client, on Yahoo data and no key.
- [TradingAgents](https://stockmarketstack.com/tools/tradingagents.md) — Analyst, bull, bear, risk and portfolio-manager agents argue over one ticker.
- [AI Hedge Fund](https://stockmarketstack.com/tools/ai-hedge-fund.md) — LLM investor personas score a ticker, deterministic code sizes the book, nothing trades.
- [Equibles](https://stockmarketstack.com/tools/equibles.md) — Scrapes SEC, FINRA, FRED and CFTC data into your own Postgres and serves it over MCP.
- [Financial Datasets](https://stockmarketstack.com/tools/financial-datasets.md) — US fundamentals and filings for agents, over REST and a first-party hosted MCP server.
- [FinGPT](https://stockmarketstack.com/tools/fingpt.md) — Financial LLM adapters, instruction datasets and training notebooks, all MIT.