DataBento MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATABENTO_API_KEY | Yes | Your DataBento API key (starts with `db-`) | |
| DATABENTO_DATASET | No | CME dataset for futures data (default is GLBX.MDP3) | GLBX.MDP3 |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_futures_quoteA | Get current price quote for ES or NQ futures contracts |
| get_session_infoA | Get current trading session information (Asian/London/NY) |
| get_historical_barsC | Get historical OHLCV bars for futures contracts |
| symbology_resolveB | Resolve symbols to instrument IDs or other symbol types across a date range |
| timeseries_get_rangeB | Get historical market data with flexible schemas and date ranges. Supports all Databento schemas (mbp-1, mbp-10, trades, ohlcv-1h, ohlcv-1d, etc.) |
| metadata_list_datasetsB | List all available Databento datasets with optional date range filtering |
| metadata_list_schemasB | List available data schemas for a specific dataset |
| metadata_list_publishersA | List publishers with their details, optionally filtered by dataset |
| metadata_list_fieldsA | List fields available for a specific schema with their types and descriptions |
| metadata_get_costB | Calculate the cost in USD for a historical data query before downloading |
| metadata_get_dataset_rangeB | Get the available date range for a dataset |
| batch_submit_jobA | Submit a batch data download job for large historical datasets. Returns job ID and status. Job processing is asynchronous. |
| batch_list_jobsA | List all batch jobs with their current status. Optionally filter by job states or time range. |
| batch_downloadA | Get download information for a completed batch job. Returns download URLs and metadata. Does NOT stream file content through MCP. |
| reference_search_securitiesC | Search security master database for instrument metadata |
| reference_get_corporate_actionsC | Get corporate actions (dividends, splits, etc.) for symbols |
| reference_get_adjustmentsB | Get price adjustment factors for backadjusted prices |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 17 tools
Each tool has a distinct purpose, with clear separation between batch job management, metadata queries, reference data, symbology, and timeseries retrieval. No overlapping functions are evident.
All tool names follow a consistent snake_case verb_noun pattern with domain prefixes (batch_, metadata_, reference_, symbology_, timeseries_). The verbs (get, list, search, resolve) are appropriate and uniform within their groups.
With 17 tools, the server covers batch operations, metadata exploration, reference data, symbology, and timeseries queries—an appropriate scope for a data access server without being excessive or insufficient.
The tool set covers core workflows: batch job lifecycle (submit, list, download), metadata discovery, reference data, and data retrieval. Minor gaps include lack of a job cancellation tool and individual job status endpoint, but the overall surface is well-rounded.