Advertise
MCP.so
Sign In

MCP Server

@bbookmind

Repository

Basic information

Category

Finance & Commerce

License

MIT

Author

bbookmind

Submitted by

parrotSHRUchildish

About MCP Server

AI bookkeeping for QuickBooks Online — 14 tools for auto-categorize, reconcile, monthly close, anomaly detection

MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "@bbookmind/mcp"
      ]
    }
  }
}

MCP Server tools

14

Auto-categorize Uncategorized QuickBooks transactions using learned rules (regex) + keyword dict + LLM (when connected). Returns confidence-scored suggestions. Use bookmind.approve_categorizations to apply. New categorization requests stage in 'pending' status and follow approval workflow.

Match bank feed transactions to invoices/bills by amount, date tolerance, and vendor similarity. Returns matched pairs and unmatched items. Score uses Levenshtein vendor similarity and weighted date/amount distance.

Statistical anomaly detection: duplicate payments (Map-based O(n)), vendor cost drift (>25%), IQR outliers, frequency spikes (>10/mo), round numbers (>=$100), large weekend transactions (>=$500). Returns flagged items with severity. Persists to SQLite for review.

Generate complete monthly close package: P&L, Balance Sheet snapshot, Cash Flow, top vendors, expense breakdown, overdue AR, anomaly summary, and action items. Returns formatted markdown report.

Search transactions by vendor, description, category, or amount. Supports lookback and limit.

Generate overdue invoice chase emails in friendly, firm, or escalation tone. Returns ready-to-send drafts.

Learn categorization rules from user corrections. Stores regex patterns. Rules apply to current company by default; set global=true to share across all companies under one account.

Approve pending categorization suggestions. Accepts transaction IDs or 'all' to approve everything pending. Approved transactions get status='categorized' and approved=1.

Reject pending categorization suggestions with feedback. Rejected transactions return to 'uncategorized'. Optional rule learning: set learn_rules=true and provide corrected_category, vendor_pattern, or description_pattern to auto-create a correction rule.

Undo categorization changes on transactions. Restore previous category from audit log. Accepts transaction IDs or 'all' to undo all categorizations from today's session.

Fetch transactions from QuickBooks Online for a date range. Returns normalized JSON array compatible with categorize, reconcile, anomalies, and monthly_close tools. Caches results in local SQLite.

Push approved categorizations from local SQLite back to QuickBooks Online. Creates journal entries for category reclassifications. Only syncs approved (approved=1) transactions.

Switch between connected QuickBooks companies. Sets the active company for all subsequent operations. Returns the current company info.

List all companies configured in BookMind, showing company ID, name, and association status. Allows OAuth connection for unconnected companies.

Overview

What is Mcp?

AI bookkeeping for QuickBooks Online. Open-source MCP server with 14 tools

How to use Mcp?

The README includes setup instructions such as npx @bbookmind/mcp.

Key features of Mcp

  • Zero cloud dependency — your data stays in local SQLite
  • Learns from you — every correction becomes a persistent rule
  • Model-agnostic — works with 7+ LLM providers (or rules-only mode)
  • Agent-agnostic — works with Claude, Cursor, Cline, Continue, Windsurf, VS Code Copilot, Goose
  • npm: npx @bbookmind/mcp

Use cases of Mcp

  • Connect an MCP-compatible client to this repository's service.
  • Review the README-backed setup before enabling it in production.

Frequently asked questions

1

Where is the source code for Mcp?

The source code is linked from the repository URL on this page.

2

Does Mcp include a standard MCP config?

If the README contains a parseable MCP configuration block, it is shown in the Config tab.

Comments

More Finance & Commerce MCP servers

Radikabunavi MCP (ラジ株ナビ)

Raditre

Remote MCP server for Japanese listed companies (EDINET / TDnet): financials, earnings flash, fair-value range, 6-axis score, DCF and screening. OAuth sign-in (Google / Apple), no API key needed. Free tier: 100 calls/day

Capital.com MCP

capital-com-sv

CFDs are complex instruments and come with a high risk of losing money rapidly due to leverage. 81.31% of retail investor accounts lose money when trading CFDs with this provider. You should consider whether you understa

4

SheetsFinance

SheetsFinance

Build stock models and finance spreadsheets with live market data in Google Sheets or Excel. Get ready-made DCF, WACC, dividend and portfolio models for any ticker, or have your AI assistant build a new workbook from val

Canopy API - Amazon Data for Agents

canopy-api

Amazon MCP server for real-time Amazon product data. Give Claude, ChatGPT, Cursor, or any AI agent live access to the Amazon Product Data API: search products, look up ASINs and UPC/EAN/ISBN codes, track prices and Buy B

3

ROIC.ai MCP Server

Roic AI

ROIC.ai is a financial data and stock market MCP server for AI assistants.

Advertise