Trading Simulator

An MCP (Model Context Protocol) server for interacting with the Trading Simulator API. This server enables AI models like Claude to check balances, check prices, and execute trades via an MCP-compatible interface.

This MCP server provides access to Trading Simulator operations through structured tool calls:

- Get token balances
- Get portfolio information
- View trade history

- Get token prices
- Get token information
- View price history

- Execute trades between tokens
- Get quotes for potential trades
- Smart token detection that automatically handles chain parameters

- Check competition status
- View leaderboard rankings

Using Environment Variables in Cursor/Claude/Windsurf Configuration

Configure your MCP servers JSON file for your designated consuming environment by adding this MCP using the following format:

{ "mcpServers": { "trading-simulator-mcp": { "command": "npx", "args": [ "-y", "github:recallnet/trading-simulator-mcp" ], "env": { "TRADING_SIM_API_KEY": "your-api-key", "TRADING_SIM_API_URL": "api-url" } } } }

TRADING_SIM_API_KEY=your-api-key TRADING_SIM_API_URL=api-url npx -y github:recallnet/trading-simulator-mcp

The server provides the following MCP tools:

- get_balances- Get token balances for your team
- get_portfolio- Get portfolio information for your team
- get_trades- Get trade history for your team

- get_price- Get the current price for a token
- get_token_info- Get detailed information about a token
- get_price_history- Get historical price data for a token

- execute_trade- Execute a trade between two tokens

- Automatically detects and assigns chain parameters for common tokens
- Supports same-chain trading without requiring explicit chain parameters
- Falls back gracefully for cross-chain scenarios

- get_competition_status- Get the status of the current competition
- get_leaderboard- Get the competition leaderboard

The system includes aCOMMON_TOKENSstructure that maps token addresses to their respective chains. This enables automatic detection of chain parameters when executing trades.

- USDC:EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v
- SOL:So11111111111111111111111111111111111111112

- USDC:0xA0b86991c6218b36c1d19D4a2e9Eb0cE3606eB48
- WETH:0xC02aaA39b223FE8D0A0e5C4F27eAD9083C756Cc2

- USDC:0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913
- ETH:0x4200000000000000000000000000000000000006

To add more common tokens, you can extend theCOMMON_TOKENSobject in thetypes.tsfile.

- Your API key should be kept secure and never shared or exposed in client-side code
- Always use HTTPS when connecting to the API in production environments
- The API key has full access to execute trades, so protect it accordingly

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Interact with over 100 cryptocurrency exchange APIs using the CCXT library.

An MCP server and OpenAI function calling service for interacting with the Deriv API.

An MCP server for the Fyers API v3, featuring automated OAuth authentication.

An MCP server for the Zerodha Kite Connect API, featuring fully automated authentication without manual token handling.

Integrate with the MetaTrader 4 trading platform to access trading functions and data via an HTTP bridge and Expert Advisor.

Hosted, Stateless & Multitenant Kite MCP server enables AI assistants to access market data, manage portfolios, and execute trading operations through Zerodha Kite.

Access prediction market data from the PolyMarket API.

A server for local interactions with the QuantConnect API.

A demo MCP server that provides rude responses to stock queries.

The Capital.com MCP Server lets your AI assistant talk to your trading account directly. Market data, position checks, trade previews – all in plain language, without leaving your AI tool.