Provides tools for exporting market data to Apache Parquet format, reading Parquet files, and converting Databento DBN files to Parquet for high-performance data storage and analysis.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Databento MCPShow me the 1-minute OHLCV bars for NVDA from today"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Installation
Quick Start
Get your API key from Databento
Configure your MCP client (see setup guides below)
Start querying market data through your AI assistant
Setup Guides
Claude Desktop
Add to your configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
GitHub Copilot CLI
Add the server to your Copilot CLI configuration:
Or add to your ~/.config/gh-copilot/config.yml:
See GitHub Copilot CLI MCP documentation for more details.
ChatGPT (via Developer Mode)
ChatGPT supports MCP servers through Developer Mode.
Enable Developer Mode in ChatGPT settings
Add an MCP server with the following configuration:
See OpenAI Developer Mode documentation for detailed setup instructions.
Features
Historical Data
Retrieve trades, OHLCV bars, market depth, and more
Support for all Databento schemas (trades, mbp-1, mbp-10, ohlcv-*, etc.)
Cost estimation before query execution
Smart data summaries with statistics
Live Data
Real-time market data streaming
Configurable stream duration
Multiple schema support
File Operations
Read/write DBN format files
Export to Apache Parquet
Convert between formats
Batch Processing
Submit large-scale batch jobs
Monitor job status
Download completed files
Reference Data
Symbol metadata and definitions
Symbology resolution
Dataset discovery
Publisher information
Quality & Performance
Smart caching with configurable TTL
Data quality analysis
Connection pooling
Comprehensive metrics
Available Tools
Tool | Description |
| Check API connectivity and server status |
| Retrieve historical market data |
| Stream real-time market data |
| Estimate query cost before execution |
| Get instrument definitions and mappings |
| Search for symbols with wildcards |
| List available Databento datasets |
| List available data schemas |
| Convert between symbology types |
| Submit batch data download |
| List batch job status |
| Get batch job download info |
| Cancel pending batch job |
| Download completed batch files |
| Parse and read DBN files |
| Get DBN file metadata |
| Write data to DBN format |
| Convert DBN to Parquet |
| Query and export to Parquet |
| Read Parquet files |
| Get trading session info |
| List data publishers |
| List schema fields |
| Get dataset date range |
| Get pricing information |
| Analyze data quality issues |
| Comprehensive symbol analysis |
| Server status and metrics |
| Performance metrics |
| Clear API response cache |
Configuration
Environment Variable | Description | Default |
| Databento API key (required) | - |
| Restrict file operations to directory | Current directory |
| Logging level (DEBUG, INFO, WARNING, ERROR) | INFO |
| Enable metrics collection | true |
Common Datasets
Dataset | Description |
| CME Globex (ES, NQ, CL futures) |
| Nasdaq TotalView |
| NYSE |
| Consolidated US equities |
| US options |
| ICE Futures Europe |
Common Schemas
Schema | Description |
| Individual trades |
| 1-minute OHLCV bars |
| 1-hour OHLCV bars |
| Daily OHLCV bars |
| Top of book |
| 10-level order book |
| Top bid/offer |
| Instrument definitions |
