FinOps AI Copilot MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Local port for optional server operations | 3000 |
| BACKEND_API_KEY | No | Bearer Token / API key for REST endpoints | mock-api-key-12345 |
| BACKEND_API_URL | No | Base URL of the existing REST API | http://localhost:4000/api |
| LARGE_TRANSACTION_THRESHOLD | No | Threshold to filter large payments | 50000 |
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 |
|---|---|
| getDashboardMetricsA | Retrieve high-level dashboard metrics (total volume, transaction counts, success rates, wallet balance). Useful for general business health checks. |
| findTransactionByIdA | Retrieve details of a specific transaction using its unique transaction ID (e.g. TXN12345). |
| findTransactionsC | Search for transactions with filters like status, vendor, merchant, amount range, dates, and pagination. |
| failedTransactionsB | Retrieve a list of failed transactions (helps operational debug). |
| pendingTransactionsA | Retrieve a list of pending transactions (helps track delayed settlements/payouts). |
| largeTransactionsB | Retrieve a list of transactions with amounts exceeding a specified threshold (e.g. ₹50,000). |
| retryTransactionsA | Retrieve transactions that have been retried more than once. Useful for identifying shaky payment flows. |
| vendorPerformanceB | Retrieve success rate, failure rate, volume, transaction count, and average response time for a specific vendor. |
| topVendorA | Retrieve the top processing vendor (the vendor with the highest transaction success rate). |
| worstVendorA | Retrieve the worst processing vendor (the vendor with the highest transaction failure rate). |
| vendorComparisonA | Compare performance metrics (success rates, failures, response times) of two specific vendors. |
| walletBalanceA | Retrieve today's current wallet balance. |
| walletHistoryB | Retrieve historic credit/debit transaction log and wallet balance records. |
| todayVsYesterdayA | Compare transaction count, volume, and success/failure rates for today vs. yesterday. |
| weeklyAnalyticsA | Fetch transaction count and volume breakdown for the last 7 days. |
| monthlyAnalyticsA | Fetch high level summaries (volume, transaction count, success rate) for the current month. |
| peakHourA | Find the hour of the day with the highest transaction density and processing volume. |
| merchantAnalyticsC | Retrieve volume, transaction count, and performance breakdown for merchants. |
| dailySummaryA | Retrieve a structured business operations summary for today, including total volume, transaction counts, success rates, top/worst vendors, peak hour, and AI routing recommendations. |
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 19 tools
Most tools have clearly distinct purposes, especially vendor, wallet, and trend-specific tools. However, getDashboardMetrics and dailySummary overlap noticeably, and several specialized transaction-list tools (failed, pending, large, retried) partially duplicate what findTransactions could accomplish.
All tool names use camelCase and follow a predictable noun/query pattern like failedTransactions, vendorPerformance, and walletBalance. The main deviation is that some names are verb-led (findTransactionById, getDashboardMetrics) while others are bare nouns or adjectives, which is still readable and consistent in style.
At 19 tools, the server is on the heavy side of the typical well-scoped range. The count is justified by the breadth of FinOps analytics, but several specialized transaction-list tools could potentially be consolidated, making the overall surface feel slightly bloated.
The tool set covers transaction lookup, filtering, vendor and merchant performance, wallet history, daily summaries, and trend analytics—strong coverage for a read-only FinOps copilot. Minor gaps exist, such as no direct refund/chargeback-specific analytics or flexible custom date-range comparisons beyond preset periods.