Dune Analytics MCP Server
Enables AI agents to query and analyze blockchain data from Dune Analytics, supporting execution of saved queries, ad-hoc DuneSQL queries, and access to cached results with parameter support.
README
mcp-server-dune
A Model Context Protocol (MCP) server for integrating AI agents with Dune Analytics blockchain data.
Requirements
- Python 3.11+
- Dune Analytics API key
Features
Tools
- run_query - Execute saved Dune queries and wait for results
- submit_query - Submit queries asynchronously for long-running jobs
- get_execution_status - Check the status of running queries
- get_execution_results - Retrieve results from completed executions
- run_sql - Execute raw ad-hoc DuneSQL queries
- create_query - Save new queries to your Dune library
- update_query - Modify existing queries
- archive_query - Archive queries from active workspace
Resources (dune:// scheme)
dune://query/{id}/latest- Cached results (zero credits)dune://query/{id}/sql- Query SQL definitiondune://execution/{id}/status- Execution job status
Prompts
- generate_dune_sql - Guide for writing valid DuneSQL
- analyze_result - Guide for interpreting query results
Installation
# Install from source
pip install -e .
# Or install dependencies directly
pip install fastmcp>=2.0.0 dune-client>=1.10.0 pydantic>=2.0.0
Configuration
Set your Dune API key as an environment variable:
# Linux/macOS
export DUNE_API_KEY="your-api-key-here"
# Windows Command Prompt
set DUNE_API_KEY=your-api-key-here
# Windows PowerShell
$env:DUNE_API_KEY="your-api-key-here"
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"dune": {
"command": "python",
"args": ["-m", "mcp_server_dune"],
"env": {
"DUNE_API_KEY": "your-api-key-here"
}
}
}
}
Direct Execution
# Run the server
python -m mcp_server_dune
Usage Examples
Execute a Saved Query
# Run query ID 123456 with parameters
run_query(
query_id=123456,
params={"token_address": "0x..."},
performance="medium",
limit=50
)
Execute Ad-Hoc SQL
# Run raw DuneSQL
run_sql(
sql="""
SELECT DATE_TRUNC('day', block_time) as day,
COUNT(*) as tx_count
FROM ethereum.transactions
WHERE block_time > NOW() - INTERVAL '7' DAY
GROUP BY 1
ORDER BY 1
LIMIT 100
""",
performance="medium"
)
Read Cached Results (Zero Credits)
Access the resource dune://query/123456/latest to get cached results without consuming execution credits.
DuneSQL Tips
- Addresses are bytearrays: use
0x...literals directly - Date intervals:
NOW() - INTERVAL '7' DAY - Prefer decoded tables:
uniswap_v3_ethereum.Factory_evt_PoolCreated - Always include
LIMITto prevent timeouts
Development
# Clone the repository
git clone https://github.com/your-org/mcp-server-dune
cd mcp-server-dune
# Create virtual environment
python -m venv venv
venv\Scripts\activate # Windows
# source venv/bin/activate # Linux/macOS
# Install in development mode
pip install -e ".[dev]"
# Run tests
pytest
# Run the server locally
python -m mcp_server_dune
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。