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.
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.