# Summarise spending by category and month

> Summarise spending by category and month: 1 companies fully do it, 11 with a limit, 16 carry the tag. Every listing in Bank data & open banking with the reason and a source.

- Canonical: https://www.anchorterminal.com/niches/banking-data.spending-summary/
- Markdown: https://www.anchorterminal.com/niches/banking-data.spending-summary/index.md (~1,550 tokens)
- Slim: https://www.anchorterminal.com/niches/banking-data.spending-summary/index.min.md (~330 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/niches/banking-data.spending-summary/index.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-15

One company's docs show a full fit.

| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |
| --- | --- | --- | --- | --- |
| 1 | 11 | 16 | 14 | 6 |

## What counts as done

Totals per category and per month that match the sum of the transactions, with internal transfers excluded and each transaction carrying a category from a documented taxonomy; the whole range is read without the agent losing rows to truncation.

How agents ask for it: how much did I spend on food last month; what are my top spending categories this year; which months did I spend most; give me a 12-month spending overview

## Does the job

The docs show it meets the test above, and nothing we read says otherwise.

- **Yodlee Core API (Yodlee, Inc.)**: Transactions carry a category and categoryType (TRANSFER, INCOME, EXPENSE and others) from GET /transactions/categories, and /derived/transactionSummary returns totals by category per month, week or year server-side.

## Does the job, with a limit

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

- **BankMCP (noskillish (open-source project))**: monthly_summary returns in and out per month with own-account transfers excluded and a checked list flagging incomplete reads, fixing the clipping in issue 13. No category field beyond the bank's merchant_category_code, so the agent must classify.
- **Basiq (Basiq Pty Ltd)**: Each transaction has a class from a fixed enum (payment, transfer, bank-fee, refund and others) and Enrich adds merchant detail, but class is too coarse for spending categories and there is no per-month aggregate outside the paid reports.
- **Belvo (Belvo Tecnologias Ltda.)**: Transactions carry a category from a documented enum including Transfers, but categorisation must be switched on by contacting Belvo, and there is no per-month aggregate.
- **Flinks (Flinks Technology Inc.)**: Enrich assigns a Category and SubCategory from a documented list (including Transfers) retrievable from /Categories, but Enrich is a separate paid product and no per-month aggregate was found.
- **MX Platform API (MX Technologies, Inc.)**: Each transaction carries category and top_level_category from MX's taxonomy and the list filters server-side by category guid, but there is no per-month spending total; monthly_account_balances covers balances only.
- **Plaid (Plaid Inc.)**: Each transaction carries personal_finance_category from a published taxonomy CSV, stated 95 per cent fill, including transfer categories. No aggregate endpoint, and acc-01 needed an LLM pass to correct Plaid's categories.
- **Powens (Powens SAS)**: The old categories endpoint is marked obsolete and the current Categorization feature is framed for lending; no per-month spending aggregate was found. Transactions do carry a type and counterparty.
- **Salt Edge Account Information (Salt Edge Limited)**: Each transaction has a category with categorization_confidence, and the reference lists categories plus expense and income category reports; categorisation can be disabled per client and its availability by plan was not read.
- **Tink (Tink AB)**: Transactions carry categories and the Finance Management statistics endpoint returns monthly expenses by category, but that sits in the Money Manager product with its own scope; whether transfers are excluded was not read.
- **TrueLayer (TrueLayer Limited)**: Each transaction has transaction_category (including TRANSFER) and a documented transaction_classification taxonomy, but some get no classification, CREDIT is never classified, and there is no aggregate endpoint.
- **Yapily (Yapily Ltd)**: Data Plus categorisation returns a documented tier1-tier2-tier3 taxonomy for UK and EU consumer and business accounts, but it is in beta, runs as an async job, and there is no aggregate endpoint.

## Couldn't check

The docs were closed to us, or silent. These carry no mark either way.

- **Teller (Teller, Inc.)**: Not read: teller.io's robots.txt disallows ClaudeBot, Claude-Web and anthropic-ai, so the docs were not fetched.

- not this job: Akoya (Akoya LLC): Transaction category is the bank's MCC or SIC where supplied, not a spending taxonomy, and there are no aggregates or transfer flags.
- not this job: Enable Banking (Enable Banking Oy): The FAQ says Enable Banking gives no categorisation; transactions carry only the bank's optional ISO 18245 merchant_category_code and there are no aggregate endpoints.
- not this job: GoCardless Bank Account Data (GoCardless Ltd): Raw Berlin Group transactions only: an optional merchantCategoryCode, no category taxonomy and no aggregate endpoint.

## What stops agents finishing

- categories wrong enough that the agent must re-classify
- a response too long for the agent to read whole, so rows are dropped
- transfers between own accounts not marked

## Around it

Before: banking-data.connect-consent, banking-data.sync-ledger. After: spreadsheets.chart, personal-finance.budget.

## Where this comes from

Weight 14 of 100 in Bank data & open banking: 6 of 41 accounts (Driggsby, Muse, Lunch Money, Tiller, the BankMCP eval, the CSV workaround); the job assistants are sold for

As data: https://www.anchorterminal.com/api/v1/use-cases/banking-data.spending-summary.json, or the MCP tool get_use_case with id banking-data.spending-summary. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp
