dune-mcp-server
Dune Analytics
Documentation
Dune Analytics MCP Server
A Model Context Protocol (MCP) server that bridges Dune Analytics data to AI agents, providing access to DEX metrics, EigenLayer operators and AVS stats, and token balances on Solana. The tools utilize the preset endpoints and echo endpoints provided by Dune.
Features
- Tools:
- `get_dex_pair_metrics`: Get essential metadata and statistical data for a given token pair on a specific chain
- `get_token_pairs_liquidity`: Find the token pair with the highest USD liquidity on a given chain
- `get_svm_token_balances`: Get token balances for a specific wallet address on Solana
- `get_eigenlayer_avs_metrics`: Get statistics for a specific AVS
- `get_eigenlayer_operator_metrics`: Get statistics for all operators in a specific AVS
- Data Formats: All results are returned in structured JSON format for easy processing
Prerequisites
- Node.js 16+ or Bun 1.0+
- A valid Dune Analytics API key (get one from Dune Analytics)
Installation
1. Clone the Repository:
git clone https://github.com/ekailabs/dune-mcp-server.git
cd dune-mcp-server2. Install Dependencies:
Using Bun:
bun installOr using npm:
npm install3. Set Up Environment Variables:
Create a `.env` file in the project root based on `.env.example`:
DUNE_API_KEY=your_api_key_hereAlternatively, set it as a system environment variable:
export DUNE_API_KEY="your_api_key_here"Usage
Running the Server
Using Bun:
# Development mode with hot reload
bun dev
# Production mode
bun start
# Or build and run
bun build src/index.ts --outdir dist
bun dist/index.jsUsing npm:
# Development mode with hot reload
npm run dev
# Production mode
npm start
# Or build and run
npm run build
npm run start:prodAdd to Claude for Desktop
To use with Claude for Desktop, add the server config:
On MacOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
On Windows: `%APPDATA%/Claude/claude_desktop_config.json`
{
"mcpServers": {
"dune": {
"command": "bun",
"args": [
"/ABSOLUTE/PATH/TO/dune-mcp-server/src/index.ts",
"stdio"
]
}
}
}Tool Usage
1. `get_dex_pair_metrics(chain, token_pair)`
2. `get_token_pairs_liquidity(chain)`
3. `get_svm_token_balances(wallet_address)`
4. `get_eigenlayer_avs_metrics(avs_name)`
5. `get_eigenlayer_operator_metrics(avs_name)`
Example Commands in Claude for Desktop
- "Can you please give me the liquidity of 'USDC-WETH' token pair on ethereum?"
- "Show me the highest liquidity token pair on arbitrum"
- "Can you please plot the stake distribution of EigenDA operators?"
- "How many stakers are there on EigenDA AVS"
License
This project is licensed under the MIT License - see the LICENSE file for details.
Running evals
The evals package loads an mcp client that then runs the index.ts file, so there is no need to rebuild between tests. You can load environment variables by prefixing the npx command. Full documentation can be found here.
OPENAI_API_KEY=your-key npx mcp-eval src/evals/evals.ts src/index.tsAcknowledgments
- Dune Analytics for their API
- Model Context Protocol for the protocol specification
Frequently asked questions
What is dune-mcp-server?
dune-mcp-server is Dune Analytics
How do I install dune-mcp-server?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is dune-mcp-server open source?
Yes — it is hosted on GitHub at https://github.com/ekailabs/dune-mcp-server and has 2 stars.
Related MCP tools
Model Context Protocol Servers
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
MCP server to provide Figma layout information to AI coding agents like Cursor
The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
Instant is the best backend for AI-coded apps. You get auth, permissions, storage, presence, and streams — everything you need to ship apps your users will love.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP