ai-trader
Backtrader-powered backtesting framework for algorithmic trading, featuring 20+ strategies, multi-market support, CLI tools, and an integrated MCP server for professional traders.
No outside reports on file
This tool can run Python code and access financial data, so only use it in isolated environments with test data, never with real trading accounts or live market connections.
Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsNo API token requiredLOW
- Package sourceGitHub (whchien/ai-trader)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/whchien/ai-trader ↗
Everything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-23.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About AI Trader
This MCP connector wraps Backtrader, a Python library for testing trading strategies before risking real money. It lets Claude analyze historical price data, run simulated trades using 20+ pre-built strategies, and generate reports—all through a chat interface rather than writing Python code directly.
Who it’s for
Traders and developers who want to test algorithmic trading ideas quickly without manual coding. People building AI assistants that need to talk about trading strategies and backtesting.
Alternatives
- Zipline (Quantopian): Similar backtesting library with Python API
- VectorBT: Vectorized backtesting for speed; less strategy templates
- MLflow + custom scripts: Build your own AI-connected backtesting without MCP
- TradingView Pine Script: Built-in strategy testing (centralized, cloud-based)
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README. Installation typically involves cloning the GitHub repository, installing Python dependencies (including Backtrader), and configuring the MCP server connection in Claude Desktop's config file. Exact steps depend on your setup.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 1.1k
- Listing last refreshed
- 2026-10-29
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- Direct market access: The tool connects to historical price data APIs and can be configured to pull live data; an attacker could redirect it to fake data sources or exfiltrate your data feeds
- Strategy injection: Malicious strategy code in GitHub or supplied by Claude could execute arbitrary Python commands on your machine
- Leaked trade logic: Your trading strategies and backtesting results may be stored in logs or passed to Claude's servers, exposing proprietary methods
- False confidence: Backtest results don't guarantee real-world performance; poor strategy selection via AI guidance could lead to financial losses
- Dependency chain attacks: Backtrader and its dependencies could be compromised; installing from untrusted sources increases risk
How to lower the risk
Least-privilege permissions
- Run in a dedicated Python virtual environment separate from other projects
- Never connect to real brokerage APIs or live market feeds
Network isolation
- Use only cached or local historical price data, not live API streams
- Disable internet access if possible; test strategies offline first
Monitoring
- Log all Claude interactions and strategy outputs to review later
- Check generated code before execution—don't auto-run suggestions
Red flags to watch for
- Claude suggesting you test with real money or live accounts
- Unexpected network requests or API calls to unknown services
- Strategy code that looks obfuscated or contains suspicious imports
Questions
How do I install AI Trader?
AI Trader does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/whchien/ai-trader.
Are there security reports about AI Trader?
No reports found for this package in our research (last checked 2026-10-30). AI Trader currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include direct market access, strategy injection, leaked trade logic.
Is AI Trader actively maintained?
AI Trader has 1.1k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/whchien/ai-trader before pinning it in production.
What are alternatives to AI Trader?
Notable alternatives to AI Trader include Zipline, VectorBT (Vectorized backtesting for speed), MLflow + custom scripts (Build your own AI-connected backtesting without MCP), TradingView Pine Script (Built-in strategy testing (centralized, cloud-based)). You can also compare AI Trader side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use AI Trader? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/whchien-ai-trader)HTML embed:
<a href="https://agentarmorhq.com/skills/whchien-ai-trader"><img src="https://agentarmorhq.com/api/badge/whchien-ai-trader" alt="AgentArmorHQ Risk Grade for AI Trader" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "whchien-ai-trader"Share with your security lead
Need sign-off to use ai-trader? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: ai-trader
- **Listing URL:** https://agentarmorhq.com/skills/whchien-ai-trader
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.1k GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (whchien/ai-trader)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/whchien/ai-trader
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- whchien
- Source code
- github.com/whchien/ai-trader
- Est. context load
- ~900 tokens / turn (~5 tool schemas, 0.45% of 200k context)
- Popularity
- 1.1k GitHub stars
- Last updated
- 2026-10-29
- Last graded
- 2026-10-23
Community
Discussions for AI Trader
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude