web3 -hub
The definitive open-source registry of Model Context Protocol (MCP) servers for Web3, blockchain, and decentralized applications. 130+ chains, DeFi, NFTs, analytics, and identity tools
claude mcp add --transport stdio rudazy-web3-mcp-hub npx -y @strangelove-ventures/web3-mcp \ --env ENABLE_SOLANA_TOOLS="true" \ --env ENABLE_BITCOIN_TOOLS="true" \ --env ENABLE_ETHEREUM_TOOLS="true"
How to use
Web3 MCP Hub serves as a centralized registry for MCP servers focused on Web3, blockchain, and decentralized applications. It aggregates production-ready MCP servers and provides ready-made configuration examples so developers can quickly connect their MCP clients to a broad set of capabilities, from multi-chain data access to on-chain actions. The hub content emphasizes categorized servers (by ecosystem and function) and includes configuration samples that show how to enable tooling across networks. To use the hub, you typically add MCP server definitions to your client configuration, referencing a package that exposes the MCP server, and specifying any needed environment variables such as API keys. For example, you can point your MCP client to a server such as the Web3 MCP server, enabling Ethereum, Solana, and Bitcoin tooling through environment flags. You can then query cross-chain data, perform transactions, or retrieve on-chain state via the MCP protocol.
The hub also demonstrates concrete configuration patterns, including how to structure the mcpServers object with command, args, and env fields. Tools available via the included servers range from multi-chain balance and transaction queries to NFT data access, on-chain governance interactions, and DeFi protocol queries. By following the examples, you can extend your client setup to incorporate additional servers from the registry and tailor access with environment variables for API keys or feature toggles.
How to install
Prerequisites:
- Node.js 18+ or Python 3.10+ (depending on how you deploy MCP servers)
- npm or yarn
- Git (optional but recommended for cloning repositories)
Installation steps:
- Install Node.js and npm from the official website or using your system package manager.
- Clone the hub repository (or install via your chosen distribution method):
git clone https://github.com/rudazy/web3-mcp-hub.git
cd web3-mcp-hub
- Install dependencies:
npm install
- Start the hub registry (or run in your preferred environment). If the repo provides a start script, use it; otherwise a typical command is:
npm run start
- Verify the registry is running and accessible, then add MCP server configurations to your client using the examples provided in the registry.
If you are deploying a specific MCP server locally, follow the respective server’s installation guide in the registry, then point your client to the server’s endpoint as described in its configuration snippet.
Additional notes
Notes and tips:
- When wiring up servers, ensure your API keys (if required) are kept secure and provided via the env field rather than hard-coded.
- The registry examples often show enabling toolsets per network (e.g., ENABLE_ETHEREUM_TOOLS, ENABLE_SOLANA_TOOLS). Adjust these flags to match the networks you intend to use.
- Validate MCP client version compatibility with the server you deploy; MCP protocol features may evolve and require corresponding client updates.
- If you encounter network or authentication errors, check environment variable names and values, and confirm network access from your deployment environment.
- Use the Quick Start sample to customize the mcpServers block for your own setup, including adding additional servers as needed.
- For large-scale deployments, consider orchestrating multiple MCP servers behind a load balancer or a gateway if supported by your MCP client.
Related MCP Servers
evm
MCP server that provides LLMs with tools for interacting with EVM networks
mcp
🤖 Taskade MCP · Official MCP server and OpenAPI to MCP codegen. Build AI agent tools from any OpenAPI API and connect to Claude, Cursor, and more.
crawlbase
Crawlbase MCP Server connects AI agents and LLMs with real-time web data. It powers Claude, Cursor, and Windsurf integrations with battle-tested web scraping, JavaScript rendering, and anti-bot protection enabling structured, live data inside your AI workflows.
awesome-finance
A curated list of MCP servers for AI finance agents
WAIaaS
Wallet-as-a-Service for all AI agents in the world
tempo
MCP server enabling AI agents to execute autonomous stablecoin payments on Tempo blockchain. Supports single/batch payments, scheduled transfers, token swaps, and balance queries with built-in spending limits, audit logging and many more