persona-financial-agent
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_MODEL | No | OpenAI model identifier used for framing. Defaults to `gpt-4o-mini`. | gpt-4o-mini |
| OPENAI_API_KEY | No | OpenAI API key used for the LLM framing step. Optional — with no key set (or on provider error), a deterministic fallback composer runs instead, so the app, API, and evals all work without it. Put it in `.env` or export it; an exported variable takes precedence over the `.env` file. | |
| SEC_USER_AGENT | No | User-Agent header for SEC's Company Facts API. Only required when rebuilding the database with live SEC data (scripts/build_db.py). Must be a real contact identity (e.g. `your-app your-real-email@your-domain.com`), not a placeholder — the build refuses to run against live SEC with a placeholder address. Not needed to run the MCP server itself against the committed database. |
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 |
|---|---|
| list_companiesB | List companies in one of the three covered sectors. |
| get_financialsB | Fetch the newest observation for each requested metric on one ticker. |
| get_hiring_signalsB | Fetch the most recent headcount/hiring signals for one ticker. |
| run_sector_screenB | Rank companies in a sector by one metric, excluding incomparable rows. |
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 4 tools
Each tool has a clear, distinct purpose: listing companies in a sector, fetching financials for a ticker, fetching hiring signals for a ticker, and screening a sector by a metric. No overlap between per-ticker and sector-level operations.
All tool names follow a consistent verb_noun pattern: list_companies, get_financials, get_hiring_signals, run_sector_screen. Naming is uniform and predictable.
Four tools is within the ideal range and the set feels focused for a niche financial persona agent. It is slightly minimal but each tool serves a distinct necessary function with no redundancy.
The tool surface covers the core workflow: browse companies, retrieve financials, retrieve hiring signals, and run sector screens. Minor gaps exist such as no historical multi-period financials or company profile details, but they are not blockers for the stated purpose.