YNAB MCP Server

Detect Recurring Charges

detect_recurring_charges

Read-onlyIdempotent

Find recurring charges in YNAB transaction history by grouping outflows by payee and exact amount, then flagging weekly, monthly, quarterly, or yearly patterns with estimated annual cost for subscription audits.

Instructions

Read-only detection of recurring charges (subscriptions, utilities, insurance) from transaction history: groups outflows by payee + exact amount and reports groups whose spacing matches a weekly/biweekly/monthly/quarterly/yearly cadence, with estimated annual cost. Use for subscription audits and 'what am I paying for' questions. Catches auto-imported recurring charges that list_scheduled_transactions cannot see (that tool only lists manually-created recurrences). Limitations: variable-amount bills (utilities that fluctuate) are missed because grouping is by exact amount; the same vendor billed under multiple identities or payee spellings appears as separate rows — verify against payee variants with search_payees before concluding a subscription was cancelled.

Input Schema

TableJSON Schema

Name	Required	Description
`budgetId`	No	Budget ID (uses default if not provided)
`monthsBack`	No	History window in months (default 6; longer windows catch quarterly/yearly cadences)
`minOccurrences`	No	Minimum occurrences to count as recurring (default 3)

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv5.4.0Sep 15, 2026
- removedOutput schema / properties / result / description
```
Removed value: -"Structured result returned by Detect Recurring Charges."
```
Addedv5.2.0Aug 29, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds meaningful behavioral context: exact-amount grouping, cadence matching, estimated annual cost, and important limitations that affect interpretation. This goes well beyond what the annotations alone convey and does not contradict them.

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 detailed yet well-structured: the core function and use case come first, followed by the key sibling distinction and then limitations. Every sentence carries essential information, and the length is justified by the tool's analytical complexity.

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 the rich annotations, complete parameter schema, and presence of an output schema, the description covers everything an agent needs to select and invoke the tool correctly. It explains what the tool catches, what it misses, and how to verify ambiguous results.

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

Parameters3/5

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

The input schema fully describes all three parameters, including defaults and the effect of monthsBack on cadence detection. The description reinforces the grouping-by-exact-amount limitation that explains why minOccurrences matters, but it does not add substantial parameter-level detail beyond the schema, so the baseline of 3 applies.

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 clearly states the tool's function: read-only detection of recurring charges from transaction history, with specific methodology (grouping by payee + exact amount and cadence detection). It also distinguishes itself from list_scheduled_transactions, making its purpose unambiguous.

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?

Explicit guidance is provided for when to use this tool ('subscription audits' and 'what am I paying for' questions), and when not to rely on it (variable-amount bills, payee spelling variants). It also names the alternative tool and the verification step with search_payees, giving clear decision criteria.

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