TradeSearcher Agent Tools
Enables interactive access to TradeSearcher strategies and backtests via CLI and MCP, allowing agents to search, backtest, and compare trading strategies.
README
TradeSearcher Agent Tools
Use TradeSearcher strategies and existing backtests inside Claude Code, Codex, and other coding agents.
Install
npm install -g @tradesearcher/cli
For MCP:
{
"mcpServers": {
"tradesearcher": {
"command": "npx",
"args": ["-y", "@tradesearcher/mcp-server"],
"env": {
"TRADESEARCHER_API_KEY": "your_api_key"
}
}
}
}
CLI
tradesearcher auth login
tradesearcher auth status
tradesearcher search BTCUSD
tradesearcher best AAPL
tradesearcher backtest 12345 --details --trades --trade-limit 20
tradesearcher strategy 6789 --source
tradesearcher export 12345 --pine --out strategy.pine
tradesearcher compare 12345 67890
tradesearcher schema
tradesearcher schema backtest
Useful search sorts:
tradesearcher search BTCUSD --sort sharpe
tradesearcher search BTCUSD --sort profitFactor
tradesearcher search BTCUSD --sort roi
tradesearcher search BTCUSD --sort latestTradeDate
tradesearcher search BTCUSD --sort robustness
--equity can return large JSON arrays. Use it after narrowing to final candidates.
Use tradesearcher schema to print JSON command schemas for agents. Use tradesearcher schema backtest or tradesearcher schema strategy for one command.
Search, best, and compare rows show source available, source no, or source private when TradeSearcher knows whether Pine source text is available. available means TradeSearcher has source text for the strategy; it does not prove that the text is a complete standalone Pine strategy.
Export Pine source for a backtest strategy:
tradesearcher export 12345 --pine --out strategy.pine
Free accounts hide high-performance backtests with a profit factor above 3. Premium shows these stronger backtests, more results, recent trades, and full strategy details.
Upgrade: https://tradesearcher.ai/app/premium
MCP tools
See docs/mcp-tools.md for tool schemas, examples, and the recommended agent workflow.
Release check
Before publishing:
npm run release:check
See docs/release.md for the publish order.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.