Take a Trial Balance CSV export from QuickBooks Online, Xero, Zoho Books, or Wave (source auto-detected from headers — YTD columns indicate Xero, Opening Balance indicates Zoho, etc.) and run three checks: (1) tb.unbalanced — debits ≠ credits (every downstream P&L / BS / cash-flow report built fr...
AI agents call analyze_trial_balance to retrieve information from HelloBooks AI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
csvText | string | Yes | Raw CSV text of a Trial Balance report. Works with QuickBooks Online (Reports → Trial Balance), Xero (Reports → Trial Balance), Zoho Books (Reports → Accountant |
fileName | string | — | Optional filename for the share-page label. |
Parameters from the server's own tool schema.
Despite the financial domain (accounting/bookkeeping), this tool is purely analytical—it inspects data and reports findings. It does not create, modify, delete, or post journal entries; does not reconcile accounts or commit transactions; does not execute external operations. The sibling tools (analyze_balance_sheet, analyze_profit_loss, compare_books_to_hellobooks, etc.) all signal analysis-only roles.
From the tool's definition Tool analyzes a Trial Balance CSV export and "run[s] three checks" (unbalanced, wrong_sign, round_balance) — querying and validating bookkeeping data. The description contains no language of modification, deletion, creation, or external state changes.
Risk signalsAccepts file system path (fileName) · Bulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Take a Trial Balance CSV export from QuickBooks Online, Xero, Zoho Books, or Wave (source auto-detected from headers — YTD columns indicate Xero, Opening Balance indicates Zoho, etc.) and run three checks: (1) tb.unbalanced — debits ≠ credits (every downstream P&L / BS / cash-flow report built from this TB is wrong until fixed); (2) tb.wrong_sign — accounts whose name suggests a class (Revenue / COGS / Expense / AR / AP) carrying a balance on the wrong side (classic posting-error signal); (3) tb.round_balance — exact-multiple-of-$10,000 balances (plug-entry signal). Input is raw CSV text of a Trial Balance report. Max 5,000 rows; max 5 MB. Returns flagged accounts with severity, a roll-up showing whether the TB balances, parse diagnostics, and a shareable URL at agents.hellobooks.ai/r/{slug}. Use this when a user pastes a Trial Balance and asks "does my TB balance?", "are there sign errors?", "what looks suspicious?", or "is this TB clean?". The Trial Balance is the foundation document for every other financial statement — if it does not balance, every downstream report is invalid. It is categorised as a Read tool in the HelloBooks AI MCP Server MCP Server, which means it retrieves data without modifying state.
analyze_trial_balance accepts 2 parameters: csvText, fileName. Required: csvText. The full parameter table on this page comes from the server's own tool schema.
Register the HelloBooks AI MCP Server MCP server in PolicyLayer and add a rule for analyze_trial_balance: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches HelloBooks AI MCP Server. Nothing to install.
analyze_trial_balance is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the analyze_trial_balance rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for analyze_trial_balance. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
analyze_trial_balance is provided by the HelloBooks AI MCP Server MCP server (Meru-Fin-Tech/HelloBooks-MCP-Public). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →