Dune Analytics (Web3 SQL Analytics API) Connector for AI agents.
4 live capabilities
Query blockchain data and Web3 metrics using SQL directly from your chat.
Waiting for input…
Why people use Dune Analytics (Web3 SQL Analytics API)
Dune Analytics for Web3 SQL Data Retrieval
With this Connector, you just tell your agent to run the query. It handles the execution, waits for the data, and hands you the results in your chat. You stay in your flow and get the data you need in seconds.
What Vinkius changes
You get SQL-powered blockchain data in your chat without leaving your current app.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Finding whale movements
A researcher asks the agent to run a Dune query for specific wallet addresses and summarize the top movements in a table.
- Real-world use case 02
Verifying protocol health
A developer uses the Connector to pull the latest on-chain state of a smart contract to check for errors or successes.
- Real-world use case 03
Automating weekly reports
An analyst fetches 7 days of volume data across multiple chains to generate a market trend report automatically.
Complete set · 4capabilities
The complete Dune Analytics (Web3 SQL Analytics API) capability set.
These are the exact actions your AI can choose when you ask it to work with Dune Analytics (Web3 SQL Analytics API).
01—04
4 capabilities in this set.
Part of 4 available through Dune Analytics (Web3 SQL Analytics API).
- 01 Capability
Execute query
Trigger a specific Dune query ID with custom parameters. This starts the data pull and provides an execution ID for tracking.
- 02 Capability
Get execution results
Retrieve the rows from a finished query. Use this to bring the actual data into your agent for analysis.
- 03 Capability
Get execution status
Check if a query is pending, failed, or finished. This helps you know exactly when the data is ready to be pulled.
- 04 Capability
Cancel execution
Stop an ongoing query immediately. Use this to kill processes that are taking too long or were started with wrong parameters.
Set up in minutes
One URL. Then ask Dune Analytics (Web3 SQL Analytics API) to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Dune Analytics (Web3 SQL Analytics API) from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_eJSVmM35oPb3EQRWNnqipzpD87HbivFnslURw8ia/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Dune Analytics (Web3 SQL Analytics API), and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Dune Analytics (Web3 SQL Analytics API) for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_eJSVmM35oPb3EQRWNnqipzpD87HbivFnslURw8ia/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Dune Analytics (Web3 SQL Analytics API) URL.
- Step 03
Save and start
Save the connection and enable Dune Analytics (Web3 SQL Analytics API) in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"dune-analytics-web3-sql-analytics-api": {
"url": "https://edge.vinkius.com/vk_preview_eJSVmM35oPb3EQRWNnqipzpD87HbivFnslURw8ia/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Dune Analytics (Web3 SQL Analytics API)
Open Agent mode in chat and ask: "Using Dune Analytics (Web3 SQL Analytics API), help me...". 4 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"dune-analytics-web3-sql-analytics-api": {
"url": "https://edge.vinkius.com/vk_preview_eJSVmM35oPb3EQRWNnqipzpD87HbivFnslURw8ia/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Dune Analytics (Web3 SQL Analytics API)
Ask Copilot: "Using Dune Analytics (Web3 SQL Analytics API), help me...". 4 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"dune-analytics-web3-sql-analytics-api": {
"url": "https://edge.vinkius.com/vk_preview_eJSVmM35oPb3EQRWNnqipzpD87HbivFnslURw8ia/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Dune Analytics (Web3 SQL Analytics API)
Open Cascade and ask: "Using Dune Analytics (Web3 SQL Analytics API), help me...". 4 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"dune-analytics-web3-sql-analytics-api": {
"url": "https://edge.vinkius.com/vk_preview_eJSVmM35oPb3EQRWNnqipzpD87HbivFnslURw8ia/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Dune Analytics (Web3 SQL Analytics API)
Ask Cline: "Using Dune Analytics (Web3 SQL Analytics API), help me...". 4 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add dune-analytics-web3-sql-analytics-api --transport http "https://edge.vinkius.com/vk_preview_eJSVmM35oPb3EQRWNnqipzpD87HbivFnslURw8ia/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Dune Analytics (Web3 SQL Analytics API)
Ask Claude: "Using Dune Analytics (Web3 SQL Analytics API), show me...". 4 tools are ready
Where the request belongs
Work Dune Analytics can move forward.
This is for the Web3 analyst who's tired of jumping between Dune tabs and Excel to build reports. It's for anyone who needs to turn raw blockchain data into actual insights quickly.
Web3 Data Analyst
Pulls DeFi and NFT metrics into reports during the work week without manual exports.
Crypto Researcher
Automates the collection of ecosystem growth data for market reports and whitepapers.
Blockchain Developer
Verifies on-chain states and protocol health while staying inside their code editor.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsAlchemy
Manage blockchain data. audit wallets, NFTs, and transactions via AI.
DappRadar (Web3 Dapp & NFT Analytics)
Access real-time Web3 data via DappRadar. analyze dapps, NFT collections, and blockchain ecosystem metrics directly from your AI agent.
Bitquery (Web3 Blockchain GraphQL APIs)
Query real-time and historical blockchain data across 40+ chains including Ethereum, Solana, and Bitcoin using GraphQL.
Etherscan
Query Ethereum and EVM-compatible blockchain data—check balances, transaction history, and token transfers directly from your AI agent.
Infura (Ethereum Node RPC Provider)
Access Ethereum blockchain data via Infura. query blocks, check balances, estimate gas, and interact with smart contracts directly from any AI agent.
Nansen (Blockchain Analytics)
Access institutional-grade blockchain analytics. track Smart Money, profile wallets, and monitor real-time token flows across multiple chains.
Bring your own AI
Change the model, client or framework. Keep Dune Analytics connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Dune Analytics.
The practical details behind the request, access and result.
What can I do with the Dune Analytics MCP?
I'll use the Dune Analytics MCP to pull real-time blockchain data into my AI chat. It lets me run SQL queries on networks like Ethereum and Solana without leaving my workspace.
Can the Dune Analytics MCP query multiple blockchains?
Yes, it connects to data across Ethereum, Solana, Polygon, and other major networks. You can pull metrics from any of these chains using your existing Dune query IDs.
How do I use the Dune Analytics MCP for DeFi research?
You can ask your agent to pull specific DeFi metrics, like total value locked or volume. The Connector handles the SQL execution and brings the data straight to you for analysis.
Does the Dune Analytics MCP support custom SQL parameters?
Yes, it lets you pass custom parameters to your Dune queries. This means you can filter by dates, specific tokens, or other variables while still using your saved queries.
How does the Dune Analytics MCP help save on API costs?
You can use the cancel_execution capability to stop queries that are taking too long or were run with mistakes. This prevents wasting your Dune credits on unnecessary data pulls.
Can I use the Dune Analytics MCP in Cursor or Claude?
Yes, it works with any MCP-compatible client including Claude, Cursor, and Windsurf. Just connect the Connector and start querying blockchain data with your agent.
How do I retrieve the actual data rows from a query?
First, use execute_query to start the process and get an execution_id. Once get_execution_status shows the state is completed, use get_execution_results with that ID to fetch the data.
Can I stop a query that is taking too long to run?
Yes. You can use the cancel_execution capability by providing the active execution_id. This will immediately interrupt the ongoing query on Dune's servers.
How do I pass parameters like dates or addresses to my Dune query?
When calling execute_query, use the query_parameters field. It accepts a JSON string (e.g., '{"address": "0x...", "limit": 10}'). The agent will parse this and apply it to your SQL execution.
One connection away
Give your agent a direct line to Dune Analytics.
Connect Dune Analytics once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available