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

Enhanced Analysis with Agent Skills

For more powerful blockchain analysis, install the Blockscout Analysis skill from the agent-skills repository. This skill provides AI agents with structured guidance for execution strategies, response handling, security best practices, and workflow orchestration.

See the agent-skills README for full capabilities and installation instructions.

Configuration

Authorization

Tools reach Blockscout data through the Blockscout PRO API. Therefore you must supply your own PRO API key in the `Blockscout-MCP-Pro-Api-Key` request header.

  1. Obtain an API key: Register for a Blockscout PRO account at Blockscout Developer Portal, then generate an API key from your dashboard.
  2. Add your API key via HTTP headers:
    When making requests (either directly or via an AI agent), include your Blockscout PRO API key in the Blockscout-MCP-Pro-Api-Key header.
  3. Using with MCP clients:
    Some AI tools and MCP clients allow you to specify custom headers when adding a server connection. Paste your API key as described above.
  4. If no API key is configured: The server will default to a shared gateway key, which enforces stricter rate limits and may restrict access to certain chains or datasets.

Claude Setup

Common

Install the Blockscout connector from the Anthropic Connectors Directory:

  1. Direct link: Visit claude.com/connectors/blockscout and click Connect.
  2. Or via Settings: Go to Settings > Connectors > Browse connectors, search for "Blockscout", then click the connector in the "Used in" section and select Connect.

Note: Connectors require a paid Claude plan (Pro, Team, Max, or Enterprise).

Limitations: Due to the use of a shared access key, there may be restrictions on connector access and capabilities.

Claude Desktop

You have two options to use the official Blockscout MCP server with a PRO API key with Claude Desktop:

Option 1: MCP Bundle (MCPB) - Recommended

Best for: Easy installation and automatic updates

Download and install the pre-built MCP Bundle (.mcpb file):

  1. Download the latest blockscout-mcp.mcpb from the GitHub releases
  2. Double-click the .mcpb file to install it in Claude Desktop
  3. Configure the Blockscout PRO API Key when prompted
  4. The extension will automatically connect to the hosted Blockscout MCP service
Option 2: Docker Proxy

Best for: Users comfortable with command-line tools and custom configurations

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",
        "--headers",
        "Blockscout-MCP-Pro-Api-Key",
        "<YOUR_BLOCKSCOUT_PRO_API_KEY>",
        "--headers",
        "Blockscout-MCP-Intermediary",
        "ClaudeDesktop",
        "https://mcp.blockscout.com/mcp"
      ]
    }
  }
}

Claude Code


    claude mcp add --transport http blockscout https://mcp.blockscout.com/mcp \
        --header "Blockscout-MCP-Pro-Api-Key: <YOUR_BLOCKSCOUT_PRO_API_KEY>"

ChatGPT Apps Setup

Install the Blockscout app from the ChatGPT Apps marketplace (or search for "Blockscout" in the Apps directory), then click "Connect" to enable it for your ChatGPT account.

Limitations: Access may be limited if using a shared PRO API key.

Codex Setup

App

  1. Open Codex and go to Settings > MCP Servers > Add server.
  2. Set Name to Blockscout, select the Streamable HTTP tab, and set URL to https://mcp.blockscout.com/mcp.
  3. Under Headers, add a header with key Blockscout-MCP-Pro-Api-Key and value <YOUR_BLOCKSCOUT_PRO_API_KEY>.
  4. Save and restart the Codex app.

CLI

Codex CLI cannot attach a custom header from the command line, so configure it in two steps:

  1. Scaffold the server entry:

    codex mcp add Blockscout --url https://mcp.blockscout.com/mcp

  2. Edit ~/.codex/config.toml to add the PRO API key header and enable the streamable-HTTP MCP client (required for remote MCP servers to connect). The resulting configuration should look like this:

    [features]
experimental_use_rmcp_client = true

[mcp_servers.Blockscout]
url = "https://mcp.blockscout.com/mcp"
http_headers = { "Blockscout-MCP-Pro-Api-Key" = "<YOUR_BLOCKSCOUT_PRO_API_KEY>" }

Cursor Setup

Add the server to your Cursor MCP configuration — either the project-level .cursor/mcp.json or the global ~/.cursor/mcp.json — supplying your PRO API key via the Blockscout-MCP-Pro-Api-Key header: 

{
  "mcpServers": {
    "blockscout": {
      "url": "https://mcp.blockscout.com/mcp",
      "timeout": 180000,
      "headers": {
        "Blockscout-MCP-Pro-Api-Key": "<YOUR_BLOCKSCOUT_PRO_API_KEY>"
      }
    }
  }
}

Try Blockscout X-Ray GPT

Experience the power of the Blockscout MCP server through our showcase GPT: Blockscout X-Ray

This GPT demonstrates the full capabilities of the MCP server, providing intelligent blockchain analysis and insights. It's a great way to explore what's possible when AI agents have contextual access to blockchain data.

Available Endpoints

Available Tools (via MCP and REST API)

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