YNAB MCP Server

Get Transactions

get_transactions

Read-onlyIdempotent

Retrieve YNAB transactions filtered by type, account, category, payee, or date range. Includes pagination and delta updates for complete results.

Instructions

List transactions with filters: type ('unapproved' / 'uncategorized'), one of accountId / categoryId / payeeId, month, sinceDate, untilDate (YNAB defaults an omitted sinceDate to one year ago). Rows include import_payee_name_original, the raw bank string, for payee disambiguation. Without a delta request the result is capped at 500 rows (override with limit, up to 2000; page with offset); a capped result returns { transactions, total, returned, offset, has_more, next_offset } instead of a bare array. Prefer search_transactions to find specific rows.

Input Schema

TableJSON Schema

Name	Required	Description
`type`	No	Filter by approval/categorization status
`limit`	No	Row cap (default 500, max 2000). Ignored for delta requests.
`month`	No	Filter by month (YYYY-MM-DD, first of month)
`offset`	No	Rows to skip, in YNAB's date-ascending order; pass next_offset from a capped result.
`payeeId`	No	Filter by payee ID
`budgetId`	No	Budget ID (uses default if not provided)
`accountId`	No	Filter by account ID
`sinceDate`	No	Only return transactions on or after this date (YYYY-MM-DD). If omitted, YNAB defaults to one year ago.
`untilDate`	No	Only return transactions on or before this date (YYYY-MM-DD)
`categoryId`	No	Filter by category ID
`lastKnowledgeOfServer`	No	Delta request server knowledge. When provided, returns { transactions, server_knowledge } uncapped.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv5.4.0Sep 15, 2026

changedInput schema / properties / lastKnowledgeOfServer / description

Previous value: -"Delta request server knowledge. When provided, returns { transactions, server_knowledge }."New value: +"Delta request server knowledge. When provided, returns { transactions, server_knowledge } uncapped."

addedInput schema / properties / limit

Added value: +{
+  "description": "Row cap (default 500, max 2000). Ignored for delta requests.",
+  "maximum": 2000,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / offset

Added value: +{
+  "description": "Rows to skip, in YNAB's date-ascending order; pass next_offset from a capped result.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}

removedOutput schema / properties / result / description

Removed value: -"Structured result returned by Get Transactions."

Changed1 schema field changedv5.1.1Jul 21, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "result": {
+      "description": "Structured result returned by Get Transactions."
+    }
+  },
+  "required": [
+    "result"
+  ],
+  "type": "object"
+}

Changed2 schema fields changedv3.1.0Jul 5, 2026

changedInput schema / properties / sinceDate / description

Previous value: -"Only return transactions on or after this date (YYYY-MM-DD)"New value: +"Only return transactions on or after this date (YYYY-MM-DD). If omitted, YNAB defaults to one year ago."

addedInput schema / properties / untilDate

Added value: +{
+  "description": "Only return transactions on or before this date (YYYY-MM-DD)",
+  "type": "string"
+}

First observedv2.0.0May 28, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds substantial behavioral detail beyond that: the 500-row default cap with limit/offset pagination, the changed response shape when capped (returning metadata fields), and the YNAB default of sinceDate to one year ago. This gives the agent accurate expectations for pagination and response handling.

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

Conciseness5/5

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

The description is dense but every sentence earns its place: purpose, payee disambiguation detail, pagination rules and response shape, and a routing recommendation. It is front-loaded with the core purpose and filters, then progressively adds operational details. No filler or redundancy.

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

Completeness5/5

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

Given 11 parameters, an output schema, and the presence of sibling tools, the description covers the essential operational aspects: filters, pagination, response format differences, and the default date behavior. The output schema handles return details, and annotations cover safety. Nothing an agent needs to call this correctly is missing.

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

Parameters4/5

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

Schema coverage is 100% with descriptions for all 11 parameters, so the schema already explains each parameter. The description adds extra semantics for key parameters: the default behavior of sinceDate, the fact that limit is ignored for delta requests, and that offset follows YNAB's date-ascending order. These enrich the schema without repeating it.

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 description states a specific verb ('List') and resource ('transactions'), enumerates the available filters, and explicitly contrasts with the sibling search_transactions by saying 'Prefer search_transactions to find specific rows.' This gives an agent a clear, distinct purpose without needing to open the schema.

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

Usage Guidelines4/5

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

The description clearly says to prefer search_transactions for finding specific rows, which is an explicit alternative and a when-not-to-use condition. It also implies usage for filtered listing via the enumerated filters. However, it does not contrast with get_transaction (single transaction retrieval) or other list_* siblings, so the routing guidance is not exhaustive.

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