Documentation

apply_match_rules

apply_match_rules MCP tool reference, parameters, return type, and safety hints.

npm

What it does

Applies saved categorization rules to pending transactions, with dry-run on by default.

Signature(catch_all_account_id: string, date_from?: string | null, date_to?: string | null, dry_run?: boolean) => Record<string, unknown>
can writedry-run

Can write, but supports dry-run. Ask the agent to preview the result before committing changes.

When to use it

Use this section to decide whether the tool fits the user request before calling it.

Use it when an agent needs to prepare a change and show a preview before committing it.
Use it during statement import, duplicate review, matching, categorization, or reconciliation workflows.

Before calling

Agents should gather these facts or confirmations first.

1

Have exact values for required inputs: catch_all_account_id.

2

Start with dry_run=true, show the preview, then ask before applying the change.

3

State the intended ledger change in plain language before calling the tool.

Parameters

Required inputs are marked clearly. Optional inputs can usually be omitted unless the workflow needs them.

catch_all_account_idrequired
string

Fallback category account for rows that do not match a rule.

date_fromoptional
string | null

Start date filter in YYYY-MM-DD format.

Default: null
date_tooptional
string | null

End date filter in YYYY-MM-DD format.

Default: null
dry_runoptional
boolean

Preview the result without committing changes.

Default: true

Agent call shape

Use the exact tool name and pass arguments as structured JSON through the MCP client.

apply_match_rules

Copy this shape into agent instructions, evals, or MCP client tests.

{
  "tool": "apply_match_rules",
  "arguments": {
    "catch_all_account_id": "<catch_all_account_id>",
    "dry_run": true
  }
}

Metadata