About MCP Etherscan Server
MCP Etherscan Server is an MCP server that provides Ethereum blockchain data tools through Etherscan's API. It suits developers who want to query on-chain information from within an MCP-compatible client.
Key features
- 01Check ETH balance for an address
- 02View recent transaction history
- 03Track ERC20 token transfers
- 04Fetch contract ABIs and gas prices
- 05Resolve addresses to ENS names
Use cases
- 01Querying balances and transactions for an address in chat
- 02Retrieving smart contract ABIs during development
- 03Monitoring current gas prices
MCP support
This project is an MCP server running over stdio that exposes six Ethereum data tools as MCP endpoints for clients such as Claude Desktop.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP Etherscan Server
An MCP (Model Context Protocol) server that provides Ethereum blockchain data tools via Etherscan's API. Features include checking ETH balances, viewing transaction history, tracking ERC20 transfers, fetching contract ABIs, monitoring gas prices, and resolving ENS names.
Features
- Balance Checking: Get ETH balance for any Ethereum address
- Transaction History: View recent transactions with detailed information
- Token Transfers: Track ERC20 token transfers with token details
- Contract ABI: Fetch smart contract ABIs for development
- Gas Prices: Monitor current gas prices (Safe Low, Standard, Fast)
- ENS Resolution: Resolve Ethereum addresses to ENS names
Prerequisites
- Node.js >= 18
- An Etherscan API key (get one at https://etherscan.io/apis)
Installation
- Clone the repository:
git clone [your-repo-url]
cd mcp-etherscan-server
- Install dependencies:
npm install
- Create a
.envfile in the root directory:
ETHERSCAN_API_KEY=your_api_key_here
- Build the project:
npm run build
Running the Server
Start the server:
npm start
The server will run on stdio, making it compatible with MCP clients like Claude Desktop.
How It Works
This server implements the Model Context Protocol (MCP) to provide tools for interacting with Ethereum blockchain data through Etherscan's API. Each tool is exposed as an MCP endpoint that can be called by compatible clients.
Available Tools
-
check-balance- Input: Ethereum address
- Output: ETH balance in both Wei and ETH
-
get-transactions- Input: Ethereum address, optional limit
- Output: Recent transactions with timestamps, values, and addresses
-
get-token-transfers- Input: Ethereum address, optional limit
- Output: Recent ERC20 token transfers with token details
-
get-contract-abi- Input: Contract address
- Output: Contract ABI in JSON format
-
get-gas-prices- Input: None
- Output: Current gas prices in Gwei
-
get-ens-name- Input: Ethereum address
- Output: Associated ENS name if available
Using with Claude Desktop
To add this server to Claude Desktop:
-
Start the server using
npm start -
In Claude Desktop:
- Go to Settings
- Navigate to the MCP Servers section
- Click "Add Server"
- Enter the following configuration:
{ "name": "Etherscan Tools", "transport": "stdio", "command": "node /path/to/mcp-etherscan-server/build/index.js" } - Save the configuration
-
The Etherscan tools will now be available in your Claude conversations
Example Usage in Claude
You can use commands like:
Check the balance of 0x742d35Cc6634C0532925a3b844Bc454e4438f44e
or
Show me recent transactions for vitalik.eth
Development
To add new features or modify existing ones:
- The main server logic is in
src/server.ts - Etherscan API interactions are handled in
src/services/etherscanService.ts - Build after changes:
npm run build
License
MIT License - See LICENSE file for details
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.