Initial project structure

[mars-steven]

Summary

This PR establishes the initial structure for the Gemini Developer Platform repository, including:

• MCP Server (packages/mcp-server/) — A Model Context Protocol server that exposes the Gemini exchange API as tools for AI assistants (Claude, ChatGPT, etc.). Covers market data, order management, account/fund operations, margin trading, and staking.
• Code Samples (samples/) — Multi-language examples (TypeScript, Python, Go) demonstrating REST and WebSocket usage of the Gemini API, including public market data endpoints and authenticated private endpoints.
• Skills (skills/gemini-candles/) — A Claude Code skill for rendering terminal-based candlestick charts from live Gemini market data.
• Project scaffolding — Apache 2.0 license and .gitignore.

MCP Server tools

Category	Tools	Auth required
Market Data	Tickers, candles, order book, trades, auctions, price feed, funding rates	No
Orders	Place, cancel, status, active orders, trade history, volume	Yes
Funds	Balances, transfers, deposit addresses, withdrawals, bank accounts	Yes
Account	Account details, sub-accounts, roles, approved addresses	Yes
Margin	Margin account, preview, positions, funding payments	Yes
Staking	Balances, history, rates, stake, unstake	Yes

Code samples coverage

Each sample is available in TypeScript, Python, and Go:

• Public REST: ticker, price feed, order book, trade history
• Public WebSocket: real-time trades, best bid/ask stream
• Private REST: account balances, place order
• Private WebSocket: prediction market prices and orders

Test plan

• Build the MCP server: cd packages/mcp-server && npm install && npm run build
• Register the server with Claude Code and verify tools appear: claude mcp add gemini ...
• Run a public sample against sandbox: python3 samples/python/get_ticker.py btcusd
• Run an authenticated sample against sandbox with test credentials
• Verify the gemini-candles skill renders a chart in Claude Code

[github-advanced-security]

You are seeing this message because GitHub Code Scanning has recently been set up for this repository, or this pull request contains the workflow file for the Code Scanning tool.

What Enabling Code Scanning Means:

• The 'Security' tab will display more code scanning analysis results (e.g., for the default branch).
• Depending on your configuration and choice of analysis tool, future pull requests will be annotated with code scanning analysis results.
• You will be able to see the analysis results for the pull request's branch on this overview once the scans have completed and the checks have passed.

For more information about GitHub Code Scanning, check out the documentation.