analyze_qbo_journal_anomalies
MCP /mcp
Scan a QuickBooks Online "Journal Entries" CSV export for anomalies — currently round-number lines (debit or credit amounts that are exact multiples of $1,000, above a $1,000 materiality threshold). Round numbers are statistically rare in real bookkeeping and frequently indicate estimates, plugs, or fraud signals worth review. Input is raw CSV text from QBO Reports → Accountant → Journal. Max 5,000 rows; max 5 MB. Returns flagged lines with severity ($100K+ high, $10K+ medium, else low) and a shareable URL. Use this when a user pastes QBO data and asks "any anomalies?", "look for round numbers", or "anything suspicious". Tier-0 subset — HelloBooks Phase 3.0 anomaly detection in the paid product additionally catches GL outliers vs entity history, vendor-history mismatches, archived-vendor activity, and AI-narrated suspicious lines (which require the live HelloBooks account).
No account required
Request example
Connect your client to https://agents.hellobooks.ai/mcp, then call:
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "analyze_qbo_journal_anomalies",
"arguments": {}
}
}
Fill arguments using the input schema below.Complete published contract
{
"inputSchema": {
"type": "object",
"properties": {
"csvText": {
"type": "string",
"minLength": 1,
"maxLength": 5242880,
"description": "Raw CSV text of a QuickBooks Online \"Journal Entries\" report. Export from QBO: Reports → Accountant → Journal → Export as CSV. Paste the file contents directly."
},
"fileName": {
"type": "string",
"maxLength": 200,
"description": "Optional original filename, used only as a label on the share page."
}
},
"required": [
"csvText"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
},
"call": {
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "analyze_qbo_journal_anomalies",
"arguments": {}
}
}
}