FinAgent
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| financial_dataA | Retrieve financial data for a stock ticker. Args: ticker: Stock ticker symbol (e.g. "AAPL", "MSFT"). data_type: One of: quote, income_statement, balance_sheet, cash_flow, analyst_estimates, insider_trades, key_ratios. period: Reporting period — "annual" or "quarterly" (default "annual"). limit: Maximum number of periods to return (default 4). Returns: JSON string with the requested data or an error object. |
| market_newsA | Fetch recent market news articles filtered by keyword. Args: query: Keyword to search for in article titles (e.g. "earnings", "Federal Reserve", "AI"). ticker: Optional stock ticker to narrow results to a specific company (e.g. "AAPL", "TSLA"). When omitted the search scans broad-market index ETFs (SPY, QQQ, DIA). days_back: Number of days of history to consider (default 7). Returns: JSON string containing a list of article objects with keys: title, source, link, published, type, related_tickers. |
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 2 tools
market_news and financial_data have clearly distinct purposes: one retrieves news articles, the other retrieves structured financial data. There is no ambiguity about which tool to use for a given request.
Both tool names follow the same pattern of two lowercase words joined by an underscore, describing a noun (market_news, financial_data). The naming convention is fully consistent.
With only 2 tools, the server feels minimal for a financial domain. While the two tools cover distinct functions, the count is on the thin side and may not justify a dedicated server without additional capabilities.
The tools cover market news and several types of financial data (quotes, statements, estimates), but lack obvious features like historical price data, ticker search or screening, and portfolio tracking. Core reading operations are present, but the surface is not fully complete for broader financial workflows.