mcpField
D
Dune Analytics MCP Server

Dune Analytics MCP Server

Local
github.com/kukapayData & Analytics41Updated 78w ago
Repository

About Dune Analytics MCP Server

Dune Analytics MCP Server is an MCP server that makes Dune Analytics query results available to AI agents. It returns all results as CSV strings and requires a Dune API key.

Key features

  1. 01Fetch the latest results of a query by ID
  2. 02Execute a Dune query by ID and return results
  3. 03Return all results as CSV-formatted strings
  4. 04Authenticate with a DUNE_API_KEY environment variable

Use cases

  1. 01Letting an AI agent read the latest data from an existing Dune query
  2. 02Running a specified Dune query from Claude Desktop

MCP support

The server exposes get_latest_result and run_query as tools that MCP clients can call to access Dune queries.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "dune-analytics": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli"
      ]
    }
  }
}
Run commandnpx -y @smithery/cli

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@smithery/cli

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Dune Analytics MCP Server

smithery badge

A mcp server that bridges Dune Analytics data to AI agents.

Features

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

Prerequisites

  • Python 3.10+
  • A valid Dune Analytics API key (get one from Dune Analytics)

Installation

Installing via Smithery

To install Dune Analytics for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @kukapay/dune-analytics-mcp --client claude
Manual Installation

  1. Clone the Repository:

    git clone https://github.com/kukapay/dune-analytics-mcp.git
cd dune-analytics-mcp

  2. Set Up Environment Variables: Create a .env file in the project root:

    DUNE_API_KEY=your_api_key_here

    Alternatively, set it as a system environment variable:

    export DUNE_API_KEY="your_api_key_here"

Usage

Running the Server

  • Development Mode:

    mcp dev main.py

    This starts the server with hot reloading for development.

  • Install for Claude Desktop:

    mcp install main.py --name "Dune Analytics"

    Installs the server as a service for use with Claude Desktop.

Tool Usage

  1. get_latest_result(query_id)

    • Description: Retrieves the latest results of a specified Dune query.
    • Input: query_id (int) - The ID of the Dune query.
    • Output: CSV-formatted string of the query results.
    • Example: 
      get_latest_result(query_id=4853921)

  2. run_query(query_id)

    • Description: Executes a Dune query and returns the results.
    • Input: query_id (int) - The ID of the Dune query to run.
    • Output: CSV-formatted string of the query results.
    • Example: 
      run_query(query_id=1215383)
Example Commands in Claude Desktop
  • "Get latest results for dune query 1215383"
  • "Run dune query 1215383"

License

This project is licensed under the MIT License - see the LICENSE file for details.

Comments

Markdown supported

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.