Dune Analytics MCP Server

Overview

Dune Analytics MCP Server is a server that bridges Dune Analytics data to AI agents, allowing for easy access and manipulation of Dune query results.

To use the Dune Analytics MCP Server, clone the repository, set up your environment variables with your Dune API key, and run the server in development mode or install it as a service for use with Claude Desktop.

Fetch the latest results of a Dune query by ID. - Execute a Dune query by ID and retrieve results. - All results are returned as CSV-formatted strings for easy processing.

Retrieving the latest results for specific Dune queries.
Running Dune queries programmatically to integrate with AI agents.
Processing Dune query results in CSV format for further analysis.

Add to your AI client

Use these steps to connect Dune Analytics MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "dune-analytics-mcp-kukapay": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-dune-analytics-mcp-kukapay"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "dune-analytics-mcp-kukapay": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-dune-analytics-mcp-kukapay"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "dune-analytics-mcp-kukapay": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-dune-analytics-mcp-kukapay"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "dune-analytics-mcp-kukapay": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-dune-analytics-mcp-kukapay"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "dune-analytics-mcp-kukapay": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-dune-analytics-mcp-kukapay"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "dune-analytics-mcp-kukapay": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-dune-analytics-mcp-kukapay"
      ]
    }
  }
}

FAQ

What are the prerequisites to run the server?

You need Python 3.10+ and a valid Dune Analytics API key.

How do I install the server?

Clone the repository and set up your environment variables as instructed in the documentation.

Can I run multiple queries at once?

The server is designed to handle one query at a time, but you can run multiple instances if needed.