Mofi

Get recurring spending patterns

mofi_recurring_get

Read-onlyIdempotent

Find repeated spending by payee (merchant or Pix recipient) and amount in an explicit period of at most 366 days. Monetary values use { amount, currency } with amount as an exact decimal string. Pending debits count and drop once posted. These are spending patterns, not confirmed subscriptions; fixed installments can resemble recurring charges. Cadence confidence is heuristic, not a probability; category confidence reflects recognized-category coverage. Own-account transfers (incl. Pix to your own CPF), card payments, refunds and investments are excluded. Separate refunds without a reliable provider link cannot be reconciled. At most 10,000 eligible transactions are analyzed; meta.historyComplete is false if more rows exist. Pass page.nextCursor unchanged. Pagination is best-effort. nextExpectedDate is predicted, not a bill.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "mode": "<mode>",
      "where": "<where>"
    },
    "name": "mofi_recurring_get"
  }
}

Input Schema

Name	Required	Description	Default
`mode`	Yes
`page`	No
`where`	Yes

Output Schema

Name	Required	Description
`data`	No
`meta`	No
`mode`	No
`page`	No
`error`	No	Typed error (code, message, retryable, details); set when isError is true.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive and closed-world, but the description adds substantial operational context on top: a 10,000-transaction analysis cap with meta.historyComplete=false when exceeded, best-effort pagination with an unchanged cursor requirement, pending debits counted until posted, and heuristic (not probabilistic) cadence confidence. It also warns that nextExpectedDate is predicted, not a bill. This is exactly the kind of behavior an agent needs before trusting the output.

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

Conciseness4/5

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

Front-loaded with the core definition and then packed with constraints; nearly every sentence carries distinct information. It is dense, however, and the caveat sentences (refund reconciliation, installments resembling recurring charges) could be tightened without losing meaning.

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?

For a nested, oneOf-based query tool with an output schema, the description covers the remaining gaps: scope limits, exclusion rules, row caps, pagination behavior, and the semantics of confidence and predicted-date fields in the response. An agent can call this correctly and interpret the result without further documentation.

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 description coverage is 0% for property text, so the description has to compensate, and it does on the two things the schema omits: the hard 366-day maximum on the period (not encoded in the schema) and the instruction to pass page.nextCursor unchanged. The oneOf variants and defaults are self-documenting in the schema, but mode=query and timezone semantics are left unexplained.

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

Purpose4/5

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

States a specific verb and resource: "Find repeated spending by payee (merchant or Pix recipient) and amount in an explicit period." It also disambiguates the concept from confirmed subscriptions and installments, so an agent knows this is pattern detection rather than a subscription feed. It does not name or differentiate from siblings like mofi_spending_get or mofi_spending_summary_get, which keeps it from a 5.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: the 366-day explicit-period requirement and the exclusions (own-account transfers, card payments, refunds, investments) tell the agent what data is in scope. There is no explicit when-to-use-this-vs-another-tool guidance against the spending siblings, and no stated prerequisites or failure conditions beyond the row cap.

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

All Mofi tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.