MCP-Finance-Reconciliation
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
auxilab-mcp-finance-recon
MCP Server for Month-End Close Reconciliation
Finance Shared Services · GBS/SSC · Auxiliobits
Automate the most manual, error-prone activities in a shared services team:
bank reconciliation, GL close, intercompany matching, and month-end close tracking.
What it does
MCP Tool | Description |
| Match bank CSV vs GL cash ledger — ±3 day date proximity, exact amount |
| Compare prior vs current GL extract — new entries, reversals, variances |
| Entity A vs Entity B — gross mismatch, FX component, risk flag |
| Rules-based break classification with recommended next actions |
| 12-task close tracker with overdue detection and risk rating |
Related MCP server: HelloBooks AI MCP Server
Quick Start
1. Install
git clone https://github.com/auxiliobits/auxilab-mcp-finance-recon
cd auxilab-mcp-finance-recon
pip install -e ".[dev]"2. Generate test data
python data/generate_test_data.pyThis creates data/sample_data/ with 7 synthetic CSV files — no real data required.
3. Run the standalone demo
python demo.pyExpected output: full 5-step reconciliation flow ending with a Month-End Readiness Report.
4. Start the MCP server (for Claude Desktop / agent use)
python src/server.pyMCP Server Config (claude_desktop_config.json)
{
"mcpServers": {
"finance-recon": {
"command": "python",
"args": ["/path/to/auxilab-mcp-finance-recon/src/server.py"]
}
}
}Tool Reference
match_bank_statement
{
"bank_csv": "<CSV string>",
"gl_csv": "<CSV string>",
"opening_balance": 500000.00
}Returns: reconciliation_summary, matched_pairs, unmatched_bank_items, unmatched_gl_items
Matching logic:
Amount match: exact within ±$0.01
Date proximity: ±3 calendar days
Tiebreaker: rapidfuzz
token_sort_ratioon description
reconcile_gl_accounts
{
"period_a_csv": "<prior period CSV>",
"period_b_csv": "<current period CSV>",
"account_name": "Accrued Liabilities — 2110"
}Returns: reconciliation_statement, new_entries, removed_entries, reversals, common_entries
check_intercompany_balances
{
"entity_a_csv": "<Entity A ledger CSV>",
"entity_b_csv": "<Entity B ledger CSV>",
"entity_a_name": "Auxiliobits India",
"entity_b_name": "Auxiliobits Singapore",
"base_currency": "USD"
}Returns: summary (with mismatch_risk: NONE/LOW/MEDIUM/HIGH/CRITICAL), matched_transactions, entity-only lists, mismatch_detail
Demo scenario: Entity A = $125,000 receivable · Entity B = $123,500 payable → $1,500 mismatch, flagged HIGH
classify_reconciliation_breaks
{
"breaks_csv": "<unreconciled items CSV>"
}CSV columns: reference, date, description, amount, source
Classification categories:
Category | Rule |
Timing Difference | Keywords: transit, outstanding, cut-off, clearing |
Missing Entry | Keywords: missing, not posted, unposted |
Duplicate Posting | Keywords: duplicate, double post, twice |
Currency Rounding | Amount ≤ $10, or FX/forex keywords |
Intercompany Mismatch | Keywords: interco, entity, subsidiary |
Unknown | No rule matched — escalate |
track_month_end_close
{
"tasks_csv": "<tasks CSV>",
"close_deadline": "2024-11-30",
"as_of_date": "2024-11-29"
}CSV columns: account_name, owner, status, due_date
Valid statuses: complete, in progress, not started, overdue, on hold
Risk logic:
CRITICAL: deadline ≤ 1 day with outstanding tasks, or deadline passedHIGH: deadline ≤ 2 days with >3 outstanding, or ≥3 overdue tasksMEDIUM: completion < 75% or any overdueLOW: on track
Project Structure
auxilab-mcp-finance-recon/
├── src/
│ ├── server.py # MCP server — tool registry + dispatch
│ └── tools/
│ ├── __init__.py
│ ├── bank_matcher.py # Bank ↔ GL matching (Pandas + rapidfuzz)
│ ├── gl_reconciler.py # Prior vs current GL extract diff
│ ├── intercompany_checker.py # Entity A vs Entity B
│ ├── break_classifier.py # Rules-based break classifier
│ └── close_tracker.py # Month-end task tracker
├── data/
│ ├── generate_test_data.py # Synthetic CSV generator
│ └── sample_data/ # Generated CSVs (gitignored)
├── tests/
│ └── test_tools.py
├── demo.py # Full 5-step demo runner
├── pyproject.toml
└── README.mdTech Stack
Component | Library |
MCP protocol |
|
Matching logic |
|
Fuzzy description matching |
|
CSV parsing |
|
Break classification | Rules-based (regex) — no LLM required |
Demo Data Summary
File | Rows | Notes |
| 50 | Unique amounts, full month |
| 48 | 45 match bank (±1-2 day drift), 3 GL-only timing items |
| 20 | October GL extract |
| 25 | 15 carry-forward + 8 new + 2 reversals |
| 3 | $125,000 receivable |
| 3 | $123,500 payable — $1,500 mismatch |
| 12 | 4 complete, 3 overdue, deadline in 1 day → HIGH risk |
| 8 | Covers all 6 break categories |
License
MIT · Built for the Auxiliobits Hackathon — Financial Reconciliation Pillar
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
AI agents for bookkeeping, reconciliation, and financial close for SMBs.
Governed rebate & revenue close (ASC 606/705/842): explain, ingest, compute, trace to source.
Documents in, reconciled double-entry books out. Statements, invoices, receipts, matched and posted.
Startup books from live bank and billing feeds: P&L, balances, approvals, period close.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceAutomates comprehensive accounting workflows including bookkeeping, tax planning, payroll processing, sales tax compliance, and client management. Integrates with QuickBooks and processes financial documents with AI-powered transaction categorization and compliance monitoring.1-
- AlicenseAqualityBmaintenanceAI agents that automate bookkeeping, bank reconciliation, and month-end financial close for SMBs and CA firms.261MIT
- AlicenseAqualityDmaintenanceAn intelligent bookkeeping MCP server for QuickBooks Online that enables natural language control over categorization, reconciliation, monthly close, and anomaly detection.1414 npmMIT
- FlicenseBqualityCmaintenanceEnables AI assistants to perform financial reconciliation with a deterministic proof engine: intake files, match transactions, verify proofs, resolve exceptions, and sign off on balanced journals under the user's authority.21-