Google Antigravity + GoldRush

Set up Google Antigravity with GoldRush

1. 1Install Google Antigravity

   Download Antigravity from antigravity.google and open your project. Free during public preview for macOS, Windows, and Linux.

2. 2Install GoldRush CLI

   Query onchain data directly from your terminal, useful for testing queries before using them in Antigravity.

   npm install -g @covalenthq/goldrush-cli

3. 3Add GoldRush MCP server

   Open the MCP Store via the "..." dropdown in the agent panel, search for GoldRush, and click Install. Or add it manually to your mcp_config.json.

   {
     "goldrush": {
       "command": "npx",
       "args": ["-y", "@covalenthq/goldrush-mcp-server"],
       "env": { "GOLDRUSH_API_KEY": "YOUR_API_KEY" }
     }
   }

4. 4Open the Antigravity chat panel

   Use the built-in Gemini chat or the Manager view for parallel agent tasks.

5. 5Start querying onchain data

   Ask: "Use the GoldRush MCP tools to get token balances for vitalik.eth on Ethereum and Base"

Things to ask Google Antigravity

Once GoldRush is connected, ask in plain words. Google Antigravity picks the calls.

• “Get the ETH balance for this wallet address”
• “Show me recent transactions for this address on Base”
• “Generate a GoldRush SDK client with typed balance methods”
• “Add an API route that returns NFT holdings for a wallet”
• “Create a React hook that fetches token prices from GoldRush”
• “Use the Manager to analyze this wallet across 5 chains in parallel”
• “Build a TypeScript utility for multi-chain balance aggregation”
• “Refactor this component to use the GoldRush SDK instead of raw fetch”

Common workflows

• Parallel multi-chain analysis

  1. Open the Manager view in Antigravity
  2. Assign separate agents to fetch data from different chains via GoldRush MCP
  3. Each agent queries balances, transactions, or pricing independently
  4. Review the aggregated results in a single workspace

• Build a Web3 feature

  1. Open a component file and start a Gemini chat session
  2. Ask Antigravity to add GoldRush balance fetching with the MCP tools
  3. It generates the integration with typed imports and error handling
  4. Use the built-in browser to test the live output

• Full-stack debugging with onchain data

  1. Open the built-in browser alongside your code
  2. Ask Antigravity to debug a failing blockchain query
  3. It uses GoldRush MCP tools to compare expected vs actual API responses
  4. Apply the fix and verify in the integrated browser

• Migrate to GoldRush

  1. Ask Antigravity to analyze your current blockchain data layer
  2. It plans a migration from raw RPC calls to the GoldRush SDK
  3. Antigravity generates multi-file changes with proper typing
  4. Review the diff and accept the coordinated migration

npx skills add covalenthq/goldrush-agent-skills

• Foundational API

  REST endpoints for historical blockchain data. Balances, transactions, NFTs, token prices, security checks, cross-chain queries across 100+ networks.

• x402

  Pay-per-request access without API keys. Agents pay with stablecoins using the HTTP 402 protocol. No accounts, no rate limits, no key management.

• CLI

  Terminal-first blockchain data with native MCP support. 17 commands that work for both humans and AI agents.

More agents

• Claude Code

  Anthropic's agentic coding tool that lives in your terminal and understands your codebase end-to-end.

• Codex

  OpenAI's cloud-native coding agent that runs tasks in a sandboxed environment with full autonomy.

• Gemini CLI

  Google's open-source terminal AI agent powered by Gemini models with built-in MCP support and a file-based skill system.