Skip to main content
Glama

openfinance_list_transactions

Read-onlyIdempotent

Returns transactions for a bank account (BANK or CREDIT type). For CREDIT (credit card) accounts, this is the ONLY way to get itemized transactions (purchases, subscriptions, etc.). Each credit card transaction MAY carry creditCardMetadata.billId pointing at a bill from openfinance_list_credit_card_bills, but this is a per-connector HINT, not authoritative: some connectors (e.g. Nubank) populate it sparsely (many transactions and installments arrive with no billId) or inconsistently (the same payment tagged to more than one bill). Do NOT reconstruct a bill's total by summing transactions by billId — the bill's own totalAmount from openfinance_list_credit_card_bills is the source of truth. CREDIT PENDING vs POSTED varies by connector: where the bank exposes future-dated status:'PENDING' installments, those represent the OPEN bill plus future bills (future months); where it does NOT, only the last closed bill's POSTED items appear until ~closing. Same query, different coverage per bank (upstream). To get a standardized open-bill total / total debt regardless, use openfinance_list_credit_card_bills (open_bill / total_pending_debt). SCHEDULED (future-dated) ROWS: results are ordered by date DESCENDING, and on a card with long installment plans the TOP of the list is the FUTURE — rows dated months ahead are scheduled installments of purchases already made, not new purchases. Every such row is flagged scheduled:true, the response carries scheduled_count and a notice naming the most recent row that actually happened. NEVER read the first row as 'the latest purchase' without checking scheduled. To list only what already happened, pass to = today. Supports from/to date filters (ISO YYYY-MM-DD) and an optional keyword filter via search_queries (case- and accent-insensitive substring match against description and merchant name, OR semantics across multiple terms). When search_queries is set the tool aggregates up to 5000 transactions within from/to before filtering — narrow from/to if truncated:true is returned. PAGINATION: OMIT both page and page_size (the default) to get ALL transactions in the from/to range in one call — the tool auto-paginates the upstream and returns them under a single logical page (page:1, totalPages:1), up to a 5000 ceiling (truncated:true + warning if exceeded, then narrow from/to). Passing page and/or page_size switches to MANUAL pagination: you get one page (page_size items, default 50, max 500; page defaults to 1) with the REAL total/totalPages, so page_size:5 alone returns the first 5 with totalPages telling you how many pages remain. On upstream errors, returns { total:0, results:[], warning, error } instead of throwing. detail controls how much per-row data you get (default 'compact' = slim, cheap). Use detail:'rich' to enrich each row (when the bank connector provides it) with merchantInfo (estabelecimento: businessName/razão social, cnpj, cnae, category — useful for auto-classifying spending) and extra creditCardMetadata fields: billId (a per-connector HINT toward the transaction's bill — sparse/inconsistent on some connectors like Nubank, so do NOT sum by it to get a bill total; use the bill's totalAmount instead), billForecastDate, cardNumber, purchaseDate, payeeMCC, feeType/feeTypeAdditionalInfo, otherCreditsType/otherCreditsAdditionalInfo. billForecastDate ("YYYY-MM") is the counterpart of billId for the OPEN cycle: PENDING transactions have NO billId (the bank only mints it once the bill closes), so this is the only field telling you which bill a pending purchase will land in — its month OFFSET is per-connector (some banks month+1, others month+0), so surface it as-is and do not derive a due date from it. cardNumber (last 4 digits) separates the primary cardholder's charges from an additional card's when several cards share one account_id. Use detail:'raw' to get the FULL untouched Pluggy transaction object (everything Pluggy returns, un-normalized — heaviest, for when you need a field we don't project). 'rich'/'raw' add tokens per row and coverage varies by bank/Open Finance, so keep the default for normal listings. For the card's statement closing/due dates use openfinance_list_accounts (creditData.balanceCloseDate / balanceDueDate). The response opens with an account echo block ({ account_id, bank, name, number, type, item_id }) identifying WHICH account/bank these transactions belong to. When more than one bank is connected, ALWAYS cross-check the echo against the account you intended to query and name the bank when presenting results — never attribute one bank's transactions to another. If total is 0 for a CREDIT account, check the connection health via openfinance_get_item_status — statusDetail.creditCards.isUpdated: false means the credit card sync failed and a force sync (openfinance_force_sync) or reconnection may be needed. May include a provider_incident block when the Open Finance provider has an OPEN incident affecting a connected bank: transactions may come back incomplete or wrong until the provider recovers, and reconnecting does not fix it.

Bulk support: accepts account_ids for batched execution.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toNo
fromNo
pageNo
detailNo
page_sizeNo
account_idYes
account_idsNo
search_queriesNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Added
  2. Removed
  3. Added
  4. Removed
  5. Added
  6. Removed
  7. Added
  8. Removed
  9. First observed

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations are generic readOnly/idempotent/destructive hints, so the description carries the full behavioral burden and does so massively: it discloses per-connector incoherence of PENDING vs POSTED, the date-DESC ordering that puts future scheduled installments at the top, the switch between auto-pagination and manual `page`/`page_size` modes, returning `{ total:0, results:[], warning, error }` instead of throwing, provider_incident/wrong data, and the token-cost implication of feature. None of this is derived from annotations, and nothing contradicts them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The definition is one enormous 100% of nearly 1500 words of text with almost no paragraph/heading structure; the same `do not sum by billId` warning appears twice, and the scheduled/future-row caveat is repeated. The opening sentence does front-load the purpose, but the critical `account` echo cross-check and connection-health instructions are buried near the bottom. Greater discrimination would make high-value warnings digestible for an agent operating at invocation time.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter finance tool with no output schema, the description is almost complete: it documents the response envelope (`account` echo, `scheduled_count`, `notice`, `truncated`, `warning`, `error`), the 5,000-row ceiling, both pagination modes, steady the enriched per-row metadata for `rich` and `raw`, and even parts of the provider-incident path. Missing bits are the shape of a default compact transaction row and a clear declaration of bulk-mode interaction between `account_id` and `account_ids`, but these are minor against the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema description coverage at 0%, the description compensates every parameter: from/to are ISO YYYY-MM-DD, `search_queries` is case-/accent-insensitive substring OR semantics, `page`/`page_size` has fully explained default-versus-manual modes, and `detail` has default, list of values and cost/impact for `rich` and `raw` are detailed. The only small gap is the relation between the single `account_id` and the bulk `account_ids` list, which is ambiguous but the rest of the parameters are described far better than most tools.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence states a precise verb+resource: `Returns transactions for a bank account (BANK or CREDIT type)`. It then explicitly marks this tool as `the ONLY way to get itemized transactions` for credit-card accounts, distinguishing it cleanly from siblings like `openfinance_list_transactions_by_item` and `openfinance_list_credit_card_bills`. An agent can tell what this tool is and what it is not without opening any other schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description names alternatives with concrete selection conditions: use `openfinance_list_credit_card_bills` for a standardized open-bill total, route to `openfinance_list_accounts` for closing/due dates, and check `openfinance_get_item_status` when a CREDIT account returns total 0. It also gives explicit negative instructions — do not reconstruct a bill total from `billId` sums, and do not treat the first row as 'latest purchase' when `scheduled:true` appears. These are the strongest kind of when-to-use/when-not-to-use signals.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation3/5

The openfinance_* tools are mostly distinct resource/action pairs, but several boundaries blur: openfinance_list_transactions vs openfinance_list_transactions_by_item vs openfinance_get_credit_card_bill(include_transactions) all return transaction data, and openfinance_get_item_status / openfinance_provider_status / openfinance_list_connections all concern connection health. The monolithic marketplace tool also bundles search/describe/invoke/install/prompt-library operations, adding further ambiguity.

Naming Consistency4/5

The 19 openfinance_* tools follow a clean snake_case verb_noun pattern (list_accounts, get_item_status, update_transaction_category), but the six platform tools break it with bare verbs (authenticate, connect) and noun-style names (marketplace, toolkit_info). The split is namespace-based and still readable, so it is only a minor inconsistency.

Tool Count3/5

25 tools is on the heavy side, but the server spans two domains: an Open Finance banking surface (accounts, bills, loans, investments, connections) and a marketplace/platform layer (auth, search, prompts, bug reporting). Many openfinance tools are necessary for that breadth, though the count is high enough to feel bloated.

Completeness4/5

The Open Finance surface is nearly complete: connections can be searched, listed, disconnected, force-synced, and health-checked; accounts, transactions, bills, loans, and investments all have read/detail paths; transaction categories can be updated. Minor gaps exist, such as no granular marketplace tools outside the monolithic marketplace tool and no single-transaction detail endpoint, but core workflows do not dead-end.