Databento

Provides access to historical, live, and reference Databento market data via an MCP interface with cost estimates and data quality features.

python

0

GitHub Stars

python

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "deepentropy-databento-mcp": {
      "command": "databento-mcp",
      "args": [],
      "env": {
        "DATABENTO_API_KEY": "your-api-key"
      }
    }
  }
}

You run the Databento MCP server to query and manage Databento market data through an MCP client. It provides historical, live, and reference data access with tooling for cost estimation, data conversion, and batch processing, all via a standardized MCP interface that you can connect to from your preferred client.

How to use

Start by installing the MCP package, then configure your MCP client to point to your local Databento MCP server, and finally begin asking questions or issuing data requests through your AI assistant. You can connect using standard MCP clients or environments mentioned in setup guides, supply your API key for authentication, and choose from historical, live, batch, and reference data endpoints. The server handles data retrieval, streaming, caching, and format conversions, and it can estimate costs before running heavy queries.

How to install

pip install databento-mcp

# Prerequisites
# - Python and pip installed on your system
# - Network access to install Python packages

# Optional verification step
databento-mcp --help

# Configuration example for local use (via standard MCP client flow)
# You will primarily provide your API key to authenticate requests.

Configuration and usage notes

Configure your MCP client to supply your Databento API key. You can set the key in environment variables for the MCP server to read, and you can use different clients in parallel by adding separate MCP server blocks with their own API keys as shown in the setup examples.

Additional setup options

You can integrate the MCP server with several clients, including Claude Desktop, GitHub Copilot CLI, and ChatGPT in Developer Mode. Each setup provides a local command to run the MCP server and requires your Databento API key. Use the corresponding configuration snippet for your client and supply the key at runtime.

Available tools

health_check

Check API connectivity and server status

get_historical_data

Retrieve historical market data

get_live_data

Stream real-time market data

get_cost

Estimate query cost before execution

get_symbol_metadata

Get instrument definitions and mappings

search_instruments

Search for symbols with wildcards

list_datasets

List available Databento datasets

list_schemas

List available data schemas

resolve_symbols

Convert between symbology types

submit_batch_job

Submit batch data download

list_batch_jobs

List batch job status

get_batch_job_files

Get batch job download info

cancel_batch_job

Cancel pending batch job

download_batch_files

Download completed batch files

read_dbn_file

Parse and read DBN files

get_dbn_metadata

Get DBN file metadata

write_dbn_file

Write data to DBN format

convert_dbn_to_parquet

Convert DBN to Parquet

export_to_parquet

Query and export to Parquet

read_parquet_file

Read Parquet files

get_session_info

Get trading session info

list_publishers

List data publishers

list_fields

List schema fields

get_dataset_range

Get dataset date range

list_unit_prices

Get pricing information

analyze_data_quality

Analyze data quality issues

quick_analysis

Comprehensive symbol analysis

get_account_status

Server status and metrics

get_metrics

Performance metrics

clear_cache

Clear API response cache