Finance Intelligence MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATABASE_URL | Yes | PostgreSQL connection URL (e.g., from Supabase) |
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": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| add_expenseC | Add an expense to the database. |
| list_expensesA | List all expenses from the database within a date range (inclusive). If the list contains more than 50 items, it truncates the inline results to the first 50 and exports the full dataset to a downloadable CSV spreadsheet. |
| expense_breakdownA | Summarize and breakdown expenses by columns or time units within a date range. |
| delete_expensesA | Delete expenses matching the provided filters. At least one filter must be provided to prevent accidental deletion of all records. All provided filters are combined using AND. |
| update_expensesA | Update expenses matching the target filters with the specified values. At least one target filter and one update value must be provided. All provided filters are combined using AND. |
| create_budgetA | Create one or more budget tracking limits. You can either pass single budget parameters or a list of budget dicts in 'budgets'. |
| list_budgetsA | List all budgets matching the optional filters. All provided filters are combined using AND. |
| update_budgetsA | Update budgets matching the target filters with the specified values. At least one target filter and one update value must be provided. All provided filters are combined using AND. |
| delete_budgetsA | Delete budgets matching the target filters. At least one target filter must be provided. All provided filters are combined using AND. |
| compare_budget_vs_expensesA | Get the real-time spending status compared against active budgets on a given reference date. All provided filters are combined using AND. |
| expense_summaryA | Generate an analytical expense summary with a rich Matplotlib chart. At least one grouping dimension ('period' or 'group_by') is recommended. |
| financial_health_scoreC | Calculate a deterministic financial health score and feedback metrics. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| resources | Read Fresh each time so you can edit the file without restarting |
TDQS
Scored across 12 tools
Each tool targets a distinct aspect of expense or budget management. The analytical tools (expense_breakdown, expense_summary, compare_budget_vs_expenses) have some conceptual overlap, but their descriptions clarify the differences (tabular grouping vs. chart-based summary vs. real-time comparison). The CRUD tools are clearly separated by resource (expenses vs. budgets).
Most tools follow a verb_noun pattern (list_expenses, add_expense, delete_budgets), but three tools are noun phrases (expense_breakdown, expense_summary, financial_health_score). There is also a minor inconsistency with 'add_expense' vs. 'create_budget', using different verbs for the same create action.
With 12 tools, the server is well-scoped for a financial management domain. Each tool serves a clear purpose, covering CRUD for expenses and budgets plus analytical insights, without excessive fragmentation or unnecessary overlap.
The tool surface provides full CRUD for both expenses and budgets, with list operations that support filters to act as read-by-query. Analytical coverage is strong with breakdown, summary, budget comparison, and health score, leaving no obvious dead ends for typical expense-tracking workflows.