
Cotrader
- Updated March 2, 2026
- get-cotrader/cotrader-mcp
CoTrader is an MCP server that screens 11,000+ stocks with natural language and surfaces chart-pattern signals to your agent.
About
CoTrader is a remote Model Context Protocol server that connects your AI coding assistant to institutional-style equity screening and chart-pattern detection. developers researching fintech ideas, market-data side projects, or investment newsletters can ask for screens in everyday language instead of rebuilding screener logic or scraping quotes. The server is exposed as streamable HTTP at api.getcotrader.com and is aimed at agent workflows in Claude Code, Cursor, Codex, and similar clients. It fits the early journey when you are validating whether a finance or analytics feature is worth building, not when you are hardening execution or compliance for live trading. Treat outputs as research aids: pair them with your own risk controls, licensing checks, and regulatory constraints before any customer-facing launch.
- Natural-language screening across 11,000+ stocks via remote streamable-http MCP
- Chart-pattern detection callable from Claude Code, Cursor, and other MCP clients
- Hosted endpoint at https://api.getcotrader.com/mcp (v1.0.0)
- GitHub source: get-cotrader/cotrader-mcp
- No local npm package in catalog metadata—connect as a remote MCP server
Cotrader by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add --transport http cotrader https://api.getcotrader.com/mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Transport | HTTP |
|---|---|
| Auth | None |
| Last updated | March 2, 2026 |
| Repository | get-cotrader/cotrader-mcp ↗ |
What it does
Let your coding agent screen U.S. equities and spot chart patterns in plain English instead of juggling screener UIs.
Who is it for?
Best when you're prototyping trading tools, market newsletters, or AI research assistants and need quick equity discovery from the IDE.
Skip if: Skip if you need audited execution, brokerage integration, or compliance-ready trading systems without a separate vendor review.
What you get
Your agent can run conversational equity screens and pattern checks through one MCP remote so you can iterate on finance or research features faster.
- Agent-callable stock screens over 11,000+ symbols
- Chart-pattern detection results inside agent sessions
- Faster iteration on finance or research feature specs
By the numbers
- Screens 11,000+ stocks (per server description)
- Server version 1.0.0
- Remote transport: streamable-http at api.getcotrader.com/mcp
README.md
CoTrader MCP Server
AI-powered stock screening and chart pattern detection for Claude Desktop, Claude Code, Cursor, and other MCP-compatible AI assistants.
Screen 11,000+ US stocks using natural language and detect technical chart patterns — all from your AI assistant.
Tools
| Tool | Description |
|---|---|
screen_stocks |
Screen stocks using natural language (e.g., "RSI under 30 with price above 200 EMA") |
detect_patterns |
Detect chart patterns for a specific stock (support/resistance, trendlines, channels, etc.) |
scan_patterns |
Scan the entire universe for a specific pattern type |
search_symbols |
Search for ticker symbols by name or prefix |
get_stock_bars |
Get historical daily OHLCV price data |
Quick Start
1. Get an API Key
Sign up at getcotrader.com and create an API key at getcotrader.com/api-keys.
2. Connect Your AI Assistant
Claude Desktop
Open Settings > Integrations > Add and enter:
https://api.getcotrader.com/mcp?api_key=YOUR_API_KEY
Claude Code / Cursor / VS Code
Add to your MCP settings:
{
"mcpServers": {
"cotrader": {
"url": "https://api.getcotrader.com/mcp",
"headers": {
"X-API-Key": "YOUR_API_KEY"
}
}
}
}
3. Start Asking
- "Screen for stocks with RSI under 30 and price above their 200-day EMA"
- "Detect chart patterns for AAPL"
- "Scan for stocks forming double bottoms"
- "Show me NVDA's price history for the last 90 days"
Supported Screening Criteria
- Price: close, open, high, low, price change (1d/5d/1m/3m/6m/1y)
- Volume: volume, average volume, relative volume
- Moving Averages: SMA/EMA (10, 20, 50, 100, 200 day)
- Momentum: RSI (14), MACD, Stochastic
- Volatility: Bollinger Bands, ATR
- Fundamentals: market cap, P/E ratio, sector, industry
Supported Chart Patterns
- Horizontal support/resistance levels
- Rising and descending trendlines
- Price channels
- Double and triple bottoms
- Pennants/triangles
- Head and shoulders
Documentation
Full documentation: getcotrader.com/docs/mcp-server
License
MIT
Recommended MCP Servers
How it compares
Remote finance-data MCP integration, not a local skill that teaches market analysis methodology.
FAQ
Who is io.github.get-cotrader/cotrader for?
Developers using MCP agents who want natural-language stock screening and chart-pattern detection during idea and research work.
When should I use io.github.get-cotrader/cotrader?
Use it while exploring finance or analytics product ideas, validating screen criteria, or drafting features that need market-discovery APIs from your agent.
How do I add io.github.get-cotrader/cotrader to my agent?
Register the remote MCP URL https://api.getcotrader.com/mcp (streamable-http) in your client’s MCP config, then invoke the server’s tools from Claude Code, Cursor, or another compatible host.