Blockscout MCP Server

This server wraps Blockscout APIs and exposes blockchain data—balances, tokens, NFTs, contract metadata—via the Model Context Protocol (MCP) so that AI agents and tools (like Claude, Cursor, or IDEs) can access and analyze it contextually.

Key Features

Contextual blockchain data access for AI tools
Multi-chain support via dynamic Blockscout instance URL resolution
Unified server architecture serving both MCP and REST API endpoints
Custom instructions for the MCP host to effectively use the server
Intelligent context optimization to conserve LLM tokens while preserving data accessibility
Smart response slicing to prevent context overflow with seamless pagination
Opaque cursor pagination using single strings instead of complex parameter sets
Automatic truncation of large data fields with clear indicators and access guidance
Enhanced observability with MCP progress notifications and comprehensive logging

Configuration

Claude Desktop Setup

To use the official Blockscout MCP server with Claude Desktop, add the following configuration to your claude_desktop_config.json file:

{
  "mcpServers": {
    "blockscout": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "sparfenyuk/mcp-proxy:latest",
        "--transport",
        "streamablehttp",
        "https://mcp.blockscout.com/mcp/"
      ]
    }
  }
}

Suggested First Prompt: For optimal results, start your Claude Desktop conversation with:

You are a senior analyst specializing in Ethereum-blockchain activities with almost ten years of experience. You have deep knowledge of Web3 applications and protocols.

Before responding to the user's request, prepare a short plan of the actions you will take to provide a complete response.

After executing each planned MCP-tool call, analyze the tool's output and write a concise summary explaining **how that output advances you toward the final result**. If the new information requires revising your original plan, state the revision explicitly and briefly explain why.

You can copy this prompt and paste it into your Claude Desktop conversation.

Gemini CLI Setup

To configure the Blockscout MCP server with Gemini CLI, add the following to your ~/.gemini/settings.json file:

{
  "mcpServers": {
    "blockscout": {
      "httpUrl": "https://mcp.blockscout.com/mcp/",
      "timeout": 180000
    }
  }
}

For detailed Gemini CLI MCP server configuration instructions, see the official documentation.

Note: Consider adding system prompts from GEMINI.md for enhanced blockchain analysis capabilities.

Available Endpoints

/mcp: The primary endpoint for MCP communication (JSON-RPC 2.0).
/health: A simple health check endpoint.
/llms.txt: A machine-readable file for AI crawlers.
/v1/...: Versioned REST API endpoints that mirror MCP tool functionality.

Available Tools (via MCP and REST API)

__get_instructions__: Provides custom instructions for the MCP host.
get_chains_list: Returns a list of all known chains.
get_address_by_ens_name: Converts an ENS name to its Ethereum address.
lookup_token_by_symbol: Searches for tokens by symbol.
get_contract_abi: Retrieves the ABI for a smart contract.
get_address_info: Gets comprehensive information about an address.
get_tokens_by_address: Returns ERC20 token holdings for an address.
get_latest_block: Returns the latest indexed block.
get_transactions_by_address: Gets transactions for an address.
get_token_transfers_by_address: Returns ERC-20 token transfers for an address.
transaction_summary: Provides a human-readable transaction summary.
nft_tokens_by_address: Retrieves NFT tokens owned by an address.
get_block_info: Returns detailed block information.
get_transaction_info: Gets comprehensive transaction information.
get_transaction_logs: Returns transaction logs with decoded event data.
get_address_logs: Gets logs emitted by a specific address.

For more details, please refer to the project's GitHub repository.