Finance Toolkit
500+ transparent financial methods calculated from raw statements, not third-party endpoints.
Description from the maker (original English)
Read-only access to Quicken For Mac financial data: transactions, spending, and portfolios.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
QUICKEN_DB_PATHYou need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"quicken-mac": {
"command": "npx",
"args": [
"-y",
"quicken-mac-mcp"
],
"env": {
"QUICKEN_DB_PATH": "your-value"
}
}
}
}Run this in your terminal
claude mcp add quicken-mac --env QUICKEN_DB_PATH=your-value -- npx -y quicken-mac-mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"quicken-mac": {
"command": "npx",
"args": [
"-y",
"quicken-mac-mcp"
],
"env": {
"QUICKEN_DB_PATH": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"quicken-mac": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"quicken-mac-mcp"
],
"env": {
"QUICKEN_DB_PATH": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
QUICKEN_DB_PATH envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account dweekly, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (1.6.0) reached the registry 3 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Finance Toolkit, SolidInvoice, Korea Tax Calculator
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
500+ transparent financial methods calculated from raw statements, not third-party endpoints.
Create and send invoices and quotes, manage clients, and track payments in SolidInvoice.
Korean tax calculation and tax-audit judgment MCP: 96 tools with statutory citations.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
A Claude Skill + MCP server that gives Claude read-only access to your Quicken For Mac financial data. Ask Claude about your accounts, transactions, spending by category, monthly trends, investment holdings, and more.
The database is always opened read-only — your Quicken data is never modified.
This repo ships two artifacts that share the same schema knowledge (docs/schema.md):
plugin/skills/quicken/SKILL.md) — teaches Claude to probe and read the Quicken SQLite database directly with Python 3's standard-library SQLite support. Its focused references/ cover balances, cash flow, investments, budgets, tags, and QuickFill rules. Works in Claude Code and any other Claude surface that loads skills. No native module install or MCP server process. This is the recommended path.list_accounts, query_transactions, spending_by_category, …). Use it when you're working in a non-Claude MCP client (Cursor, Cline, mcp-remote bridges) that can't load skills, or when you'd rather call typed tools than have Claude write SQL.The Claude Code plugin install (claude plugin install quicken-mac-mcp) bundles both, with the skill leading and the MCP tools available as shortcuts.
Quicken For Mac must be open while using either the skill or the MCP. Quicken encrypts its database file when the app is closed — the data is only readable while Quicken is running.
Quicken For Mac stores data in a Core Data SQLite database inside a .quicken bundle in your Documents folder (e.g., ~/Documents/MyFinances.quicken/data). The skill teaches Claude how to query that database directly; the MCP server is a thin wrapper that exposes eight prepackaged queries as tools.
claude plugin install quicken-mac-mcp
This installs both the /quicken skill (recommended path) and the MCP server. Claude will lead with the skill and fall back to the MCP tools when convenient.
Use these if you're in a non-Claude-Code client that can't load skills, or you only want the typed-tool wrapper.
claude mcp add quicken -- npx -y quicken-mac-mcp
Download the bundle for your Mac from the latest GitHub release and drag it into Claude Desktop:
quicken-mac-mcp-arm64.mcpbquicken-mac-mcp-x64.mcpbIt will prompt you for your database path (or auto-detect it).
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": { "quicken": { "command": "npx", "args": ["-y", "quicken-mac-mcp"] } } }
Restart Claude Desktop and you'll see a hammer icon with 8 tools available.
If you have multiple Quicken files, or your .quicken bundle isn't in ~/Documents, set the QUICKEN_DB_PATH environment variable:
{
"mcpServers": { "quicken": { "command": "npx", "args": ["-y", "quicken-mac-mcp"], "env": { "QUICKEN_DB_PATH": "/path/to/YourFile.quicken/data" } } } }
By default, the server auto-detects your Quicken database only when exactly one .quicken bundle exists in ~/Documents. If multiple bundles exist, it refuses to guess; set QUICKEN_DB_PATH explicitly.
These are the eight prepackaged tools the MCP server exposes. The skill covers the same ground (and more) by writing SQL directly against the database — see plugin/skills/quicken/SKILL.md.
| Tool | Description |
|---|---|
list_accounts | List all accounts with name, type, and active/closed status. Optional type filter. |
list_categories | List all category tags with parent hierarchy. Filter by expense/income. |
query_transactions | Query transactions with filters: date range, account types/names, amount range, payee search, category. Returns one row per split entry, with note (transaction-level) and split_note (per-split) memos. |
spending_by_category | Aggregate negative consumer-spending splits by category, excluding transfers and report-excluded rows and preserving (Uncategorized). |
spending_over_time | Monthly negative consumer-spending totals with the same exclusions, optionally broken down by category. |
search_payees | Search payees by name with transaction counts. |
list_portfolio | List investment holdings with shares, cost basis, and stored Quicken price quotes. |
raw_query | Run arbitrary SELECT queries (500-row limit). |
qmac)This project includes a fully featured, self-documenting command-line interface qmac that allows you to query your Quicken SQLite database directly from the terminal without going through an MCP client.
qmac spending-by-category --help).--json to get raw data for scripting.# General help
qmac --help
qmac man
qmac list-accounts --account-type checking
qmac query-transactions --start-date 2024-01-01 --end-date 2024-12-31 --payee-search costco --max-amount -100
qmac spending-by-category --start-date 2025-01-01 --end-date 2025-03-31 --group-by category
qmac list-portfolio
Want to move your complete personal financial history out of Quicken to your own sovereign, self-hosted, or custom agentic analysis platform?
This project includes a high-speed, zero-dependency, pure Python utility scripts/export_sovereign_csv.py that connects to your unlocked Quicken database and extracts it into a cleanly normalized, portable package.
python3 scripts/export_sovereign_csv.py
quicken_sovereign_export/ will be generated, containing:accounts.csv: Beautifully normalized accounts list (checking, credit, brokerage, retirement, etc.).categories.csv: Income & expense category path structure.payees.csv: Registered merchant names list.transactions.csv: Top-level ledger with post-date, notes, and transaction-level details.transaction_splits.csv: Line-item splits showing amounts and category IDs.holdings.csv: Active investment holdings reconstructed from your individual tax lots with cost basis and unrealized returns.tags.csv: Custom user tags mapped directly to splits.schema.json: Complete relational column and foreign key reference dictionary.README.md: A detailed migration guide demonstrating how to load and query your financial history instantly in DuckDB, Pandas, PostgreSQL, or other databases.This allows other agentic platforms (like custom GPTs, self-hosted LLMs, or sovereign database agents) to immediately parse, ingest, and analyze your entire financial history.
Quicken For Mac uses Core Data with these key tables:
| Table | Purpose |
|---|---|
ZACCOUNT | Bank accounts, credit cards, investment accounts |
ZTRANSACTION | Individual transactions (with ZNOTE transaction-level memo) |
ZCASHFLOWTRANSACTIONENTRY | Split line items — categories AND per-split ZNOTE memos live here |
ZTAG | Category tags with parent hierarchy (Z_ENT looked up at runtime) |
ZUSERPAYEE | Payee names |
Dates use Core Data epoch (seconds since 2001-01-01). The MCP server handles all date conversion automatically — you pass ISO 8601 dates, it returns ISO 8601 dates. The skill recipes show the conversion (+ 978307200) inline so Claude can write SQL directly.
Account types are stored as uppercase strings: CHECKING, CREDITCARD, SAVINGS, MORTGAGE, RETIREMENTIRA, ASSET, LIABILITY, LOAN, etc. The tools accept any casing.
For the full schema reference (84 entities, all tables, indexes, foreign keys, and Core Data write semantics including Z_OPT optimistic locking), see docs/schema.md.
git clone https://github.com/dweekly/quicken-mac-mcp.git
cd quicken-mac-mcp npm install npm test # run tests npm run lint # eslint npm run format # prettier npm run dev # run server locally
Set QUICKEN_DB_PATH before npm test if ~/Documents holds more than one .quicken bundle; otherwise the live-schema suites skip.
Known issues and planned work live in ROADMAP.md — open bugs, developer-experience gaps, and deferred dependency upgrades (fresh as of 2026-08-14).
docker build -t quicken-mac-mcp .
docker run --rm -v ~/Documents/YourFile.quicken:/data:ro quicken-mac-mcp
Z_ENT lookup for CategoryTag (#4), added account_names filter and date fallback for imported transactions (#5)ZTRANSACTION.ZNOTE and ZCASHFLOWTRANSACTIONENTRY.ZNOTE) and documented the Z_OPT write-back semantics now in docs/schema.md.This project is an independent, community-developed open-source tool. It is not an official Intuit product and is not endorsed by, directly affiliated with, maintained by, or sponsored by Intuit Inc. or any of its subsidiaries. "Quicken" is a registered trademark of Intuit Inc. All product and company names are trademarks or registered trademarks o
Only the beginning is shown; read the rest in the repo