Dune Analytics MCP Server

Dune Analytics MCP Server

What is Dune Analytics MCP Server about?

Provides two tools—get_latest_result and run_query—that fetch or execute Dune Analytics queries and return the results as CSV strings, enabling AI agents to consume blockchain analytics data directly.

How to use Dune Analytics MCP Server?

1. Install the server (via Smithery or manually).
2. Set the DUNE_API_KEY environment variable.
3. Start the server in development mode with mcp dev main.py or install it for Claude Desktop using mcp install main.py --name "Dune Analytics".
4. Call the exposed tools from an AI agent or Claude Desktop prompt, e.g., get_latest_result(query_id=4853921).

Key features of Dune Analytics MCP Server

• Tool get_latest_result: Retrieves the most recent results of a specified Dune query.
• Tool run_query: Executes a Dune query on demand and returns the fresh results.
• CSV Output: All responses are CSV-formatted strings, simplifying data parsing.
• Python 3.10+: Built with modern Python for easy integration.
• Simple deployment: Supports hot‑reloading development mode and one‑click install for Claude Desktop.

Use cases of Dune Analytics MCP Server

• AI‑driven financial analysis: Let language models query blockchain metrics and react to the data in real time.
• Automated reporting: Generate periodic CSV reports from Dune queries without manual API calls.
• Data enrichment for chatbots: Provide up‑to‑date on‑chain statistics to conversational agents.
• Rapid prototyping: Developers can experiment with Dune queries inside AI workflows.

FAQ from the Dune Analytics MCP Server

• Do I need a Dune API key? Yes, set DUNE_API_KEY in your environment or .env file.
• Which Python version is required? Python 3.10 or newer.
• Can I run the server locally? Yes, use mcp dev main.py for local development.
• How are results formatted? As CSV strings, ready for parsing by any tool.
• Is the project open‑source? It is released under the MIT License.

Dune Analytics MCP Server

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.