pineapplesour.github.io
Drop a bank or card statement into the tab. Nothing uploads. A WebMCP agent analyses it in place, and you watch every tool call it makes.
First seen 2026-11-05 · Last seen 2026-11-05 · Source: webmcp.com
Answer 8 · Act 7 · Transact 0 · Score: Not yet scored
Tool inspector
find_anomalies
Flag transactions worth a second look: charges far outside the normal range for that same merchant (scored against the median and MAD, so one big charge cannot hide another), the same amount billed twice within two days, and unusually large one-off payments at merchants with no history.
Page: /tallyroom/
Input schema
| Property | Type | Required | Description |
|---|---|---|---|
from |
string | no | Only include transactions on or after this date (YYYY-MM-DD). |
to |
string | no | Only include transactions on or before this date (YYYY-MM-DD). |
category |
string | no | Restrict to one category. Use 'Uncategorised' for rows with no category yet. |
account |
string | no | Restrict to accounts whose name contains this text. |
merchant |
string | no | Restrict to a merchant. Matching is fuzzy, so 'starbucks' catches every branch and spelling. |
search |
string | no | Free-text match against the transaction description. |
flow |
string | no | Which side of the ledger to include. Defaults to all. |
minAmount |
number | no | Minimum absolute amount. |
maxAmount |
number | no | Maximum absolute amount. |
sensitivity |
number | no | Robust z-score threshold for outliers. Lower finds more. Defaults to 3.5. |
Raw JSON schema
{
"type": "object",
"properties": {
"from": {
"type": "string",
"description": "Only include transactions on or after this date (YYYY-MM-DD)."
},
"to": {
"type": "string",
"description": "Only include transactions on or before this date (YYYY-MM-DD)."
},
"category": {
"type": "string",
"description": "Restrict to one category. Use 'Uncategorised' for rows with no category yet."
},
"account": {
"type": "string",
"description": "Restrict to accounts whose name contains this text."
},
"merchant": {
"type": "string",
"description": "Restrict to a merchant. Matching is fuzzy, so 'starbucks' catches every branch and spelling."
},
"search": {
"type": "string",
"description": "Free-text match against the transaction description."
},
"flow": {
"type": "string",
"enum": [
"all",
"spend",
"income"
],
"description": "Which side of the ledger to include. Defaults to all."
},
"minAmount": {
"type": "number",
"description": "Minimum absolute amount."
},
"maxAmount": {
"type": "number",
"description": "Maximum absolute amount."
},
"sensitivity": {
"type": "number",
"description": "Robust z-score threshold for outliers. Lower finds more. Defaults to 3.5."
}
}
}
Similar websites
bahi.naklitechie.com
Double-entry books for an Indian business in one browser tab: invoices, GST returns, TDS and TCS, inventory and your CA's review, kept in one file on your own d…
dashboard.orderly.network
Orderly dashboard
fin-esse-beta.vercel.app
A WebMCP-powered financial planning workspace where you and an AI agent reason across your loans, portfolio, budget and goals together.
bankgraph.app
Investigate individual U.S. banks, the banking system, and economic context with public FDIC filings and direct-agency data.