AuraStream MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EIA_API_KEY | No | EIA API key (free at https://www.eia.gov/opendata/register.php), required to use the eia source. | |
| OANDA_TOKEN | No | Oanda API token, required to use the oanda source. | |
| FRED_API_KEY | No | FRED API key, required to use the fred source. | |
| ALPACA_API_KEY | No | Alpaca API key, required to use the alpaca source. | |
| CENSUS_API_KEY | No | US Census API key (free at https://api.census.gov/data/key_signup.html), required to use the uscensus source. | |
| FINNHUB_API_KEY | No | Finnhub API key, required to use the finnhub source. | |
| POLYGON_API_KEY | No | Polygon API key, required to use the polygon source. | |
| EDGAR_USER_AGENT | No | Your name and contact email, e.g. 'Your Company contact@yourcompany.com'. Required by the SEC and needed to use the edgar source; no registration required. | |
| OANDA_ACCOUNT_ID | No | Oanda account ID, required to use the oanda source. | |
| ALPACA_SECRET_KEY | No | Alpaca secret key, required to use the alpaca source. | |
| OANDA_ENVIRONMENT | No | Oanda environment, either 'practice' (default) or 'live'. Optional; used with the oanda source. | practice |
| AURASTREAM_API_KEY | Yes | Your AuraStream API key. Required for all data requests. Get a free key from https://aurastream.unbiased-alpha.com. | |
| AURASTREAM_API_URL | No | Overrides the AuraStream API endpoint (useful for testing). |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_sourcesA | List the AuraStream data sources: what each covers, ticker format, intervals, supported dtypes, optional source-specific parameters, the fields returned when they are not OHLCV, and whether provider credentials are needed and configured. Free to call (does not use the API allowance). |
| get_timeseriesA | Fetch historical data from AuraStream and return it as a CSV table per ticker (timestamp,Open,High,Low,Close,Volume for market bars; source-specific fields otherwise, see list_sources). Long results are cut to the most recent max_rows rows per ticker, with the total row count noted. Each call uses one unit of the user's monthly AuraStream allowance. Provider credentials come from the server's environment; never ask the user to paste them. |
| get_latestA | Return the most recent N bars (OHLCV) per ticker, without having to pick dates. Uses one unit of the monthly AuraStream allowance. Data is historical/delayed, not a live quote; the last bar may still be forming. |
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 3 tools
get_timeseries and get_latest both fetch bar data, but the descriptions clearly separate them (explicit date ranges vs. most-recent N bars), and list_sources is a distinct discovery tool. An agent could occasionally pick the wrong fetch tool, but the split is well-explained. Naming edges toward the same verb, which slightly increases the chance of misselection between the two read tools.
All three tools follow a consistent snake_case verb_noun pattern: get_timeseries, get_latest, list_sources. The pattern is predictable and readable, and no conventions are mixed.
Three tools is slightly thin, but the server's purpose is narrow read-only market/source data, and each tool earns its place. A small surface is appropriate here rather than over-scoped.
The core workflow (discover sources, fetch historical ranges, fetch latest bars) is fully covered with sensible allowance and truncation behavior. Minor gap: no ticker search/metadata lookup to resolve valid symbols before fetching, which an agent must work around via list_sources.