MCP Directory

Dune Analytics MCP Server

Bridge Dune Analytics on-chain query results to AI agents as CSV.

Unverified
stdio (local)
API key
Stale
Python
View repo 40

Add to your client

Copy the config for your MCP client and paste it into its config file.

Install / run
npx -y @smithery/cli install @kukapay/dune-analytics-mcp --client claude

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "dune-analytics-mcp-server": {
      "command": "mcp",
      "args": [
        "install",
        "main.py",
        "--name",
        "Dune Analytics"
      ],
      "env": {
        "DUNE_API_KEY": "your_api_key_here"
      }
    }
  }
}

Step-by-step guides: Add to Claude Desktop · Add to Cursor · Add to Windsurf

Before you start

  • Python 3.10+
  • A valid Dune Analytics API key (get one from https://dune.com/settings/api)
  • The mcp CLI / MCP-capable client such as Claude Desktop

About Dune Analytics MCP Server

An MCP server that bridges Dune Analytics data to AI agents. It provides two tools for fetching the latest results of a Dune query and for executing a Dune query by ID, returning all results as CSV-formatted strings. Built in Python and intended to run locally over stdio with a Dune Analytics API key.

Tools & capabilities (2)

get_latest_result

Fetch the latest (cached) results of a Dune query by ID. Input: query_id (int). Output: CSV-formatted string of the query results.

run_query

Execute a Dune query by ID and retrieve the results. Input: query_id (int). Output: CSV-formatted string of the query results.

When to use it

  • Pulling the latest results of an existing Dune dashboard query into an AI assistant for summarization or analysis.
  • Triggering a fresh run of a Dune query and feeding the on-chain metrics into an agent workflow.
  • Exporting blockchain/DeFi query results as CSV for downstream processing by a model.

Security notes

Requires a Dune Analytics API key supplied via the DUNE_API_KEY environment variable. Treat the key as a secret; do not commit the .env file. The run_query tool executes Dune queries against your account, which may consume Dune API credits.

Dune Analytics MCP Server FAQ

What do I need to run this server?

Python 3.10+ and a valid Dune Analytics API key set via the DUNE_API_KEY environment variable. You can get an API key from https://dune.com/settings/api.

How do I install it for Claude Desktop?

Use the Smithery CLI: 'npx -y @smithery/cli install @kukapay/dune-analytics-mcp --client claude'. Alternatively, clone the repo, set DUNE_API_KEY, and run 'mcp install main.py --name "Dune Analytics"'.

What format are results returned in?

Both tools return results as CSV-formatted strings, which makes them easy for AI models and downstream tooling to parse.

What is the difference between get_latest_result and run_query?

get_latest_result fetches the most recent cached results of a query without re-executing it, while run_query triggers a fresh execution of the query before returning the results.

#dune-analytics#blockchain#on-chain-data#crypto#analytics#sql#web3

Alternatives to Dune Analytics MCP Server

Compare all alternatives →
Memory (Knowledge Graph)
AI, Data & Knowledge
74k

Official MCP server providing persistent, file-backed knowledge-graph memory across sessions.

Verified
stdio (local)
No auth
TypeScript
9 tools
Updated 5 months agoRepo
Sequential Thinking
AI, Data & Knowledge
62k

Structured step-by-step reasoning tool for breaking problems into revisable thought sequences.

Verified
stdio (local)
No auth
TypeScript
1 tool
Updated 6 months agoRepo
AWS Knowledge MCP
AI, Data & Knowledge
7.0k

Fully managed remote server for AWS docs, blogs, What's-New and Well-Architected guidance — no key.

Verified
HTTP (remote)
No auth
Hosted
6 tools
Updated 5 months agoRepo

Compare Dune Analytics MCP Server with:

vs Memory (Knowledge Graph)vs Sequential Thinkingvs AWS Knowledge MCPvs MCP Server Chart