Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Personal Agent Tax Deduction & Freelancer Expense Categorizer audit my bank transactions for Schedule C deductions and tax savings"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Official Website: https://www.genpark.ai
LinkedIn: https://www.linkedin.com/company/92955550 (https://www.llinkedin.com/company/92955550)
Personal Agent Tax Deduction & Freelancer Expense Categorizer. Audits bank transactions and receipts against IRS Schedule C expense categories (home office, software, mileage, meals), calculates tax liability deductions, and isolates audit risk flags.
GenPark Official Website: https://www.genpark.ai
LinkedIn Official Page: https://www.linkedin.com/company/92955550 (https://www.llinkedin.com/company/92955550)
Related MCP server: dingdawg-finance-agent
100% Zero External Dependencies: Runs entirely on the Python 3.9+ standard library.
Model Context Protocol (MCP) Standard: Native support for JSON-RPC 2.0 initialize, tools/list, and tools/call.
Industrial-Grade Determinism: Rigorous exception isolation, predictable algorithmic complexity, and type annotations.
Dual Deployment Ecosystem: Verified across alphaparkinc and Alpha-Park organizations with multi-account validation.
from client import PersonalAgentTaxDeductionCategorizer
def main():
agent = PersonalAgentTaxDeductionCategorizer()
bills = [
{"merchant": "AWS Cloud", "amount_usd": 184.50, "description": "Compute clusters for development"},
{"merchant": "Logitech", "amount_usd": 129.99, "description": "MX Master 3S Ergonomic Mouse"},
{"merchant": "Bistro Deluxe", "amount_usd": 290.00, "description": "Investor dinner"}
]
res = agent.categorize_deductible_expenses(bills, marginal_tax_bracket_pct=32.0)
print("--- Personal Tax Deduction Analysis ---")
print(f"Total Spent: ${res['total_spent_usd']} | Total Deductible: ${res['total_deductible_usd']}")
print(f"Estimated Tax Savings: ${res['estimated_tax_savings_usd']}")
for exp in res['categorized_expenses']:
print(f"* [{exp['schedule_c_category']}] {exp['merchant']}: ${exp['deductible_amount_usd']} (Audit Flag: {exp['audit_flag']})")
if __name__ == "__main__":
main()
Start standard JSON-RPC 2.0 server over stdio:
python mcp_server.pyExecute embedded test harness:
python mcp_server.py --testInspect skill.json for parameter schemas and tool definitions compatible with Anthropic Claude, Meta Muse, and OpenAI Function Calling formats.
Licensed under the MIT License. Copyright © 2026 GenPark AI. Follow us on LinkedIn: https://www.linkedin.com/company/92955550 | https://www.llinkedin.com/company/92955550
This server cannot be deployed
Receipt ingestion, Gmail capture, expense analysis, and reviewed reports for AI-agent workflows.
Open-source AI accounting skills verified by licensed accountants (tax, VAT, payroll).
Turn bank statement PDFs into categorized, balance-checked transactions and reports.
Double entry accounting run by your own AI: books, VAT figures, invoices, month close (UK, DE, AT).
