Robinhood Chain EVM MCP
A zero-dependency MCP server that bridges AI agents to Robinhood Chain and Arbitrum Orbit L2 networks, enabling querying balances, simulating transactions, and signing/broadcasting EVM transactions via JSON-RPC tools.
README
Robinhood Chain EVM Web3 MCP Server
A zero-dependency, pure Python Model Context Protocol (MCP) server specifically tailored for Robinhood Chain (and general Arbitrum Orbit Layer-2 networks).
This server acts as a Web3/EVM bridge, allowing local AI agents (e.g., Claude, Cursor, Gemini CLI) to read states, estimate gas, simulate execution, and sign/broadcast transactions directly on-chain using simple JSON-RPC tools.
Why This Matters
Traditional developers entering a newly launched blockchain (like Robinhood Chain, launched July 2026) face significant friction:
- Context Window Bloat: Passing complex, multi-thousand-line JSON ABIs to an LLM wastes tokens and causes memory degradation.
- AI-to-Web3 Gap: AI models cannot natively compute gas, sign transactions, or verify contract logic without extensive boilerplate code.
This tool solves both:
- Simplified Signatures: Uses a local SQLite cache to store complex ABIs, exposing only human-readable, minimal signatures (e.g.,
transfer(address,uint256)) to the LLM. - Autonomous Execution: Allows the agent to query, simulate (dry-run), sign, and verify transactions autonomously when a private key is provided in the environment variables.
🚀 Pitching for the $1M Arbitrum Open House Developer Grants
Robinhood Chain has committed $1 Million to support developer activity and ecosystem growth via the Arbitrum Open House Program.
You can use this codebase to pitch for developer grants:
- Fork/Launch this server as a standalone open-source developer tool.
- Build a demo dApp/agent (e.g., a "Robinhood RWA Portfolio Manager Agent" that dynamically swaps USDG stablecoin yield into tokenized stocks like AAPL/TSLA).
- Submit to the Arbitrum / Robinhood Testnet Faucet and Open House program as an active infrastructure contribution.
🛠️ Setup Instructions (Termux / Linux)
1. Install Dependencies
pip install -r requirements.txt
2. Configure Environment variables
Create or update your ~/.env file:
# RPC Override (Default is Robinhood Mainnet)
ROBINHOOD_CHAIN_RPC_URL="https://rpc.mainnet.chain.robinhood.com"
# Private key for autonomous transaction signing (Keep this secure!)
ROBINHOOD_CHAIN_PRIVATE_KEY="0x..."
🔌 Connecting to AI Clients (MCP Setup)
1. Cursor
Go to Settings > Models > MCP and add a new server:
- Name:
Robinhood-EVM-MCP - Type:
command - Command:
python /data/data/com.termux/files/home/robinhood-evm-mcp/server.py
2. Claude Desktop
Add this to your claude_desktop_config.json (usually at ~/.config/Claude/claude_desktop_config.json):
{
"mcpServers": {
"robinhood-evm-mcp": {
"command": "python",
"args": ["/data/data/com.termux/files/home/robinhood-evm-mcp/server.py"]
}
}
}
🛠️ Exposed MCP Tools
get_evm_balance(address, token_address): Fetches native ETH or ERC-20 token balance. Supports ticker overrides (USDG,AAPL,TSLAor dynamically registered tickers).query_smart_contract(contract_address, function_name, args, abi_type): Executes a read-only query (call) on a smart contract.simulate_evm_transaction(contract_address, function_name, args, value_wei): Dry-runs a state-changing transaction and returns estimated gas details.send_evm_transaction(contract_address, function_name, args, value_wei, wait_confirm): Builds, signs, and broadcasts a transaction.get_robinhood_ticker(ticker): Retrieves the verified contract address of a tokenized stock or USDG.switch_rpc_network(network_name): Changes the active network configuration dynamically (options:robinhood-mainnet,robinhood-testnet,localhost).register_custom_abi(contract_address, abi_json): Saves custom smart contract ABIs to the local SQLite database mapping.scan_launched_tokens(force_refresh): Queries the MemeFactory smart contract on-chain to scan and index all deployed meme tokens.import_custom_token(ticker, address, name, decimals): Dynamically imports custom addresses as tickers, saving them to local SQLite cache.estimate_meme_trade_output(token_address, trade_type, amount): Simulates a bonding curve trade and computes expected output amount and price impact.buy_meme_coin(token_address, eth_amount, max_slippage, min_output_amount): Performs a buy transaction with on-chain bonding curve parameters verified pre-flight for slippage safety.sell_meme_coin(token_address, token_amount, max_slippage, min_output_amount): Performs a sell transaction with on-chain bonding curve parameters verified pre-flight for slippage safety.execute_cross_chain_bridge(src_chain_id, src_token, dest_chain_id, dest_token, amount_raw, recipient): Fetches cross-chain swap routing and transaction details, then builds, signs, and executes the bridging transaction directly on the source EVM chain.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。