A
licenseC
qualityD
maintenanceEnables querying of BudgetBakers Wallet data including accounts, transactions, categories, and labels through natural language commands.
8
38 npm
MIT
BudgetBakers MCP Server
by vmrchnk
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@BudgetBakers MCP Server Show my account balances"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
BudgetBakers MCP Server
MCP server for integrating Claude with the BudgetBakers Wallet API. Gives Claude access to financial data: accounts, transactions, categories, and spending analytics.
Quick start
Add to ~/.claude/settings.json (or Claude Desktop config):
{
"mcpServers": {
"budgetbakers": {
"command": "npx",
"args": ["-y", "budgetbakers-mcp"],
"env": {
"BUDGETBAKERS_API_TOKEN": "<your-token>"
}
}
}
}You can get the API token from BudgetBakers Wallet settings.
Related MCP server: Yodlee MCP Server
Tools
Tool | Description |
| List all accounts with balances. Filters: |
| Income/expense categories. Filter: |
| User-defined tags. Filter: |
| Search transactions. Requires |
| Full details of a single transaction by |
| Spending grouped by category for a date range |
| Income, expenses, and net cashflow for a date range |
| Top merchants by spending for a date range |
accountIdis required for transactions and analytics tools. Callget_accountsfirst to get it.
Example prompts
"Show my accounts and balances"
"How much did I spend in February?"
"What do I spend the most money on?"
"Top 5 merchants this month"
"Find all transactions at Starbucks in January"
Development
git clone https://github.com/vmrchnk/budgetbakers-mcp.git
cd budgetbakers-mcp
npm install
npm run buildTo use the local build instead of the npm package:
{
"mcpServers": {
"budgetbakers": {
"command": "node",
"args": ["/path/to/budgetbakers-mcp/build/index.js"],
"env": {
"BUDGETBAKERS_API_TOKEN": "<your-token>"
}
}
}
}Technical details
TypeScript, ES2022, Node16 modules
Dependencies:
@modelcontextprotocol/sdk,zodSupports
agentHints=true— API returns hints about pagination, rate limits, etc.Automatic pagination via hint-provided URLs
Analytics tools aggregate data server-side (API has no analytics endpoints)
Available Tools
8 toolscashflow_summaryB
Calculate income, expenses, and net cashflow for a date range.
Inputs: dateTo (required), dateFrom (required), accountId (required).
get_accountsA
Get all financial accounts with balances. Use this first to get accountId for other tools.
Inputs: currency, accountType, includeArchived.
get_categoriesA
Get income/expense categories. Use to find categoryId for filtering transactions.
Inputs: name.
get_labelsA
Get user-defined labels/tags. Use to find labelId for filtering transactions.
Inputs: name.
get_transactionA
Get full details of a single transaction by ID.
Inputs: id (required).
search_transactionsA
Search transactions with filters. accountId is required — use get_accounts first to find it.
Inputs: accountId (required), limit, payee, dateTo, +4 more.
spending_by_categoryA
Aggregate spending by category for a date range. Shows where money goes.
Inputs: dateTo (required), dateFrom (required), accountId (required).
top_merchantsB
Find merchants/payees with the highest spending in a date range.
Inputs: dateTo (required), dateFrom (required), accountId (required), limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
A3.8/5.0
Scored across 8 tools
Disambiguation5/5
Each tool targets a distinct resource or function: accounts, categories, labels, individual transactions, filtered search, and three separate analytics aggregations. There is no overlap or ambiguity between tools, even among the analytics which are clearly differentiated by output.
Naming Consistency3/5
Four tools follow a clear verb_noun pattern (get_accounts, get_categories, get_labels, get_transaction) and search_transactions also fits. However, the three analytics tools (spending_by_category, cashflow_summary, top_merchants) are noun phrases rather than imperative verbs, mixing conventions. Names remain readable and descriptive, but the inconsistency is noticeable.
Tool Count5/5
Eight tools is well-scoped for a financial data query server. The set covers account discovery, reference data, transaction retrieval/search, and analytics without bloat. Each tool earns its place and the count feels appropriate for the domain.
Completeness4/5
The server provides solid read/analytics coverage: accounts, categories, labels, single transaction, filtered search, and three aggregate views. Minor gaps include lack of a 'list all transactions' endpoint without accountId (search requires it) and no budget/balance history tools, but for a read-centric budget server these are workable limitations.
Maintenance
ActivityInactive
ResponsivenessNo recent community issues
Related MCP Connectors
Ask Claude about your income and spending, and import bank statements. No bank login.
Personal finance, bank account, and shared memory connector for Claude, ChatGPT, Gemini Spark & more
Read-only access to your own bank, card and brokerage accounts for Claude, ChatGPT and other AI agents: balances, transactions, spending, subscriptions, cashflow and investment holdings. It can never move money.
Ask your AI about your own accounts, debts, budgets and goals. OAuth sign-in, read-only by default.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceConnects Claude Desktop to Yodlee financial data, enabling account management, transaction queries, spending summaries, and audio narrations.1MIT
- AlicenseAqualityAmaintenanceConnects Claude to Credit Karma for natural-language access to transactions, spending patterns, and account summaries.11369 npm1MIT
- FlicenseNot gradedqualityDmaintenanceEnables users to manage personal expenses, analyze spending patterns, track budgets, generate reports, and export data through natural language conversations with Claude.-