SmartLedger MCP
Turn Claude into your personal bookkeeper. Parse invoices, categorize receipts by IRS Schedule C line item, analyze bank statements, and generate tax-ready expense summaries.
100% local processing. Your financial data never leaves your machine.
Tools
| Tool | What it does |
|---|---|
parse_invoice |
Extract vendor, amounts, line items, dates from invoice PDFs |
parse_receipt |
Extract merchant, total, tax, payment method from receipt PDFs |
parse_bank_statement |
Parse CSV bank exports, auto-categorize by IRS expense type |
tax_summary |
Generate IRS Schedule C deduction breakdown from bank statements |
extract_document_text |
Raw text extraction from any PDF |
Quick Start
pip install smartledger-mcp
Add to your Claude Desktop or Claude Code config:
{
"mcpServers": {
"smartledger": {
"command": "smartledger-mcp"
}
}
}
Then just tell Claude:
- "Parse this invoice" (drop a PDF)
- "Categorize my March bank statement" (drop a CSV)
- "Generate my Schedule C tax summary for Q1"
IRS Schedule C Categories
SmartLedger automatically maps transactions to 12 IRS expense categories:
| Category | Schedule C Line |
|---|---|
| Advertising | Line 8 |
| Car and Truck | Line 9 |
| Contract Labor | Line 11 |
| Insurance | Line 15 |
| Legal and Professional | Line 17 |
| Office Expense | Line 18 |
| Rent or Lease | Line 20b |
| Travel | Line 24a |
| Meals (50% deductible) | Line 24b |
| Utilities | Line 25 |
| Other Expenses | Line 27a |
| Local Transport | Line 24a |
Privacy
All document processing happens locally on your machine using pdfplumber for PDF extraction. No data is sent to any external service. No cloud. No tracking. Just local file parsing that Claude can use.
Pricing
Available on MCPize:
- Starter ($29/mo) - 100 document parses/month
- Pro ($49/mo) - Unlimited parses, all tools
Or install from PyPI for free (self-hosted, no usage limits).
Requirements
- Python 3.10+
- Claude Desktop, Claude Code, or any MCP-compatible client
License
MIT
Metadata
Release files for smartledger-mcp 0.2.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| smartledger_mcp-0.2.0.tar.gz | 14.5 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| smartledger_mcp-0.2.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 26.3 kB
Release files / smartledger_mcp-0.2.0.tar.gz
| Download URL | smartledger_mcp-0.2.0.tar.gz |
|---|---|
| Size | 14.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
46fb9da7b098db9869b97071291cab25e9321dd2e802aaee6a59c334bf4a247e
|
|
BLAKE2b-256 checksum How to use checksums |
9a136f3b94d38413900b937cca97bc9ea02c1e84c00a4d747b31743f4974206a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.3
|
Release files / smartledger_mcp-0.2.0-py3-none-any.whl
| Download URL | smartledger_mcp-0.2.0-py3-none-any.whl |
|---|---|
| Size | 11.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
7f7b12f6d67f1b597727c3302d78cea239e38e66fbbacab4d6a16145bcfc9f16
|
|
BLAKE2b-256 checksum How to use checksums |
5478f63c54d6aab41894cb2e938cf78c1942ae8221b6274ed7135c135cf99220
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.3
|
Security for smartledger-mcp 0.2.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.