Databento MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATABENTO_API_KEY | Yes | Databento API key (required) | |
| DATABENTO_DATA_DIR | No | Restrict file operations to directory | Current directory |
| DATABENTO_LOG_LEVEL | No | Logging level (DEBUG, INFO, WARNING, ERROR) | INFO |
| DATABENTO_METRICS_ENABLED | No | Enable metrics collection | true |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| health_checkA | Check the health and connectivity of the Databento API. Use this to diagnose connection issues or verify the server is working properly. |
| get_historical_dataA | Retrieve historical market data for symbols from Databento. Examples:
Tips:
|
| get_symbol_metadataC | Get metadata for symbols including symbology mappings and instrument definitions |
| search_instrumentsC | Search for instruments in a dataset |
| list_datasetsB | List all available datasets from Databento |
| clear_cacheC | Clear the API response cache |
| get_costA | Estimate the cost of a historical data query before executing it |
| get_live_dataC | Subscribe to real-time market data for a limited duration |
| resolve_symbolsC | Resolve symbols between different symbology types |
| submit_batch_jobC | Submit a batch data download job for large historical datasets |
| list_batch_jobsB | List all batch jobs with their current status |
| get_batch_job_filesC | Get download information for a completed batch job |
| get_session_infoC | Identify the current trading session based on time |
| list_publishersC | List data publishers with their details |
| list_fieldsC | List fields available for a specific schema |
| get_dataset_rangeB | Get the available date range for a dataset |
| read_dbn_fileC | Read and parse a DBN file, returning the records as structured data |
| get_dbn_metadataB | Get only the metadata from a DBN file without reading all records |
| write_dbn_fileC | Write historical data query results directly to a DBN file |
| convert_dbn_to_parquetC | Convert a DBN file to Parquet format |
| export_to_parquetC | Query historical data and export directly to Parquet format |
| read_parquet_fileC | Read a Parquet file and return the data |
| get_metricsB | Get server performance metrics and usage statistics. Returns:
Example: get_metrics(reset=false) to view current stats |
| get_account_statusB | Get comprehensive server status and account information. Returns:
Example: get_account_status() for a full server overview |
| quick_analysisA | One-call comprehensive analysis of a symbol. Combines: metadata + cost estimate + sample data + trading session info + data quality check. Example:
Returns:
|
| analyze_data_qualityA | Analyze data quality and detect issues in market data. Detects:
Returns:
Example:
|
| list_schemasB | List all available data schemas from Databento. Returns:
Example: list_schemas() |
| list_unit_pricesB | Get current pricing information per dataset/schema combination. Parameters:
Returns:
Example: list_unit_prices(dataset="GLBX.MDP3") |
| cancel_batch_jobC | Cancel a pending or processing batch job. Parameters:
Returns:
Example: cancel_batch_job(job_id="JOB-12345") |
| download_batch_filesA | Download completed batch job files to a local directory. Parameters:
Returns:
Example: download_batch_files(job_id="JOB-12345", output_dir="/data/downloads") |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| market-data-workflow | Step-by-step guide for retrieving market data from Databento |
| cost-aware-query | How to estimate costs before running expensive queries |
| troubleshooting | Diagnose and resolve common issues with the Databento MCP server |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Databento Schema Reference | Documentation of available data schemas |
| Databento Dataset Reference | Common datasets and their descriptions |
| Error Code Reference | Complete list of error codes and their meanings |
TDQS
Scored across 30 tools
Most tools have distinct purposes, but there is some overlap that could cause confusion. For example, get_account_status and get_metrics both provide server performance information, and analyze_data_quality and quick_analysis both assess data quality. However, descriptions help differentiate them, and the majority of tools target unique operations.
Tool names follow a consistent verb_noun pattern throughout, such as get_historical_data, list_datasets, and submit_batch_job. There are minor deviations like clear_cache (verb_adjective) and health_check (noun_noun), but the overall naming is predictable and readable.
With 30 tools, the count is too high for the server's purpose of market data access and analysis. Many tools feel redundant or overly granular, such as separate tools for reading DBN and Parquet files or multiple batch job operations, which could overwhelm agents and indicate poor scoping.
The tool surface is largely complete for market data operations, covering data retrieval, analysis, batch processing, and metadata. Minor gaps exist, such as no direct tool for updating or deleting data, but agents can work around this given the domain's focus on read-heavy operations.