Moneywiz MCP 服务器 | PlugMCP
跳到正文 MoneyWiz MCP Server
An MCP (Model Context Protocol) server for accessing MoneyWiz database data. This server allows ChatGPT, Claude, and other MCP-compatible clients to query your MoneyWiz financial data, analyze spending and income trends, get savings recommendations, calculate net worth, and view comprehensive financial statistics.
An MCP (Model Context Protocol) server for accessing MoneyWiz database data
把任意工具接入任意智能体。面向非开发者的 MCP 服务器目录;网关承载流量,n8n 承载应用。
产品
目录
开发者
公司
Features
List Accounts : Get all accounts with balances and currencies
Get Account Balance : Retrieve balance for a specific account
List Transactions : View recent transactions, optionally filtered by account
List Categories : Get all expense/income categories
Analyze Spending Trends : Analyze spending trends by category and time period (month/year)
Analyze Income Trends : Analyze income trends by category and time period (month/year)
Get Savings Recommendations : Get personalized savings recommendations based on income vs spending
Calculate Net Worth : Calculate total net worth from all accounts (assets minus liabilities)
Get Financial Stats : Get comprehensive financial statistics from all historical data
Installation
Prerequisites
macOS (for MoneyWiz export + Claude Desktop path conventions)
Go 1.22+ (required when installing from source)
MoneyWiz exported database folder containing ipadMoneyWiz.sqlite
1. Clone git clone <repository-url>
cd moneywiz-mcp
2. One-click install (recommended) This builds the binary, installs it to ~/.local/bin/moneywiz-mcp, and registers it in Claude clients.
If you omit --db, it reuses ~/.moneywiz-mcp/ipadMoneyWiz.sqlite or imports the newest local iMoneyWiz-Data-Backup-* export automatically.
With explicit database path (folder/sqlite):
./scripts/install.sh --db "/path/to/iMoneyWiz-Data-Backup-2025_12_21-17_23"
./scripts/install.sh --db latest
Release downloads
moneywiz-mcp-darwin-arm64
moneywiz-mcp-darwin-amd64
moneywiz-mcp-darwin-universal
SHA256SUMS
The release workflow does not publish a standalone installer yet. scripts/install.sh is source-tree based and is meant to be run from this repository.
3. Import DB to a stable path (recommended) Avoid dealing with changing export folder names by importing to:
~/.moneywiz-mcp/ipadMoneyWiz.sqlite
./scripts/import_db.sh "/path/to/iMoneyWiz-Data-Backup-2025_12_21-17_23"
Then install using the stable file:
./scripts/install.sh --db "$HOME/.moneywiz-mcp/ipadMoneyWiz.sqlite"
Or let the installer do the import automatically:
4. One-click rebuild + reinstall (debug/dev loop) Use this after local code changes. It rebuilds and re-registers in one command.
./scripts/rebuild_reinstall.sh --db "/path/to/iMoneyWiz-Data-Backup-2025_12_21-17_23"
5. Manual build (optional) go build -o moneywiz-mcp ./cmd/main.go
6. Uninstall Remove MCP registration from Claude clients and delete installed binary:
./scripts/uninstall.sh --yes
Export MoneyWiz Database
Open MoneyWiz
Go to Settings → Database & Export → Export database file
Use the exported folder that contains ipadMoneyWiz.sqlite
Usage
Running the Server Run directly with a database folder or sqlite file:
./moneywiz-mcp -db /path/to/iMoneyWiz-Data-Backup-2025_12_21-17_23
The binary accepts either:
Export folder path (it appends ipadMoneyWiz.sqlite)
Direct sqlite file path
latest (pick newest iMoneyWiz-Data-Backup-* found)
No -db (priority order below)
Path resolution priority:
-db argument
MONEYWIZ_DB_PATH env var
~/.moneywiz-mcp/ipadMoneyWiz.sqlite if present
Auto-detect newest export folder in common locations
MCP Client Configuration ./scripts/install.sh already handles configuration for:
Claude Desktop (claude_desktop_config.json)
Claude Code (claude mcp add)
Manual Configuration Claude Desktop Configuration
{
"mcpServers": {
"moneywiz": {
"command": "/Users/<you>/.local/bin/moneywiz-mcp",
"args": ["-db", "/absolute/path/to/ipadMoneyWiz.sqlite"]
}
}
}
claude mcp add --scope user moneywiz -- /Users/<you>/.local/bin/moneywiz-mcp -db /absolute/path/to/ipadMoneyWiz.sqlite
Important : Use absolute paths.
After updating the configuration:
Quit Claude Desktop completely (⌘Q)
Reopen Claude Desktop
The MCP server should connect automatically
Available Tools
list_accountsList all accounts in MoneyWiz with their balances and currencies.
{
"name": "list_accounts",
"arguments": {}
}
get_account_balanceGet the balance for a specific account by ID.
account_id (integer, required): The ID of the account
{
"name": "get_account_balance",
"arguments": {
"account_id": 249
}
}
list_transactionsList recent transactions, optionally filtered by account ID.
account_id (integer, optional): Account ID to filter transactions. If not provided, returns all transactions
limit (integer, optional): Maximum number of transactions to return (default: 50)
{
"name": "list_transactions",
"arguments": {
"account_id": 249,
"limit": 20
}
}
list_categoriesList all categories in MoneyWiz.
{
"name": "list_categories",
"arguments": {}
}
analyze_spending_trendsAnalyze spending trends by category and time period. Groups spending by month or year and provides category breakdowns.
group_by (string, optional): Group by "month" or "year" (default: "month")
months (integer, optional): Number of months to analyze (default: 6)
{
"name": "analyze_spending_trends",
"arguments": {
"group_by": "month",
"months": 6
}
}
Returns : Array of spending trends with:
period: Time period (YYYY-MM or YYYY)
total_spending: Total spending for the period
transaction_count: Number of transactions
by_category: Map of category names to spending amounts
analyze_income_trendsAnalyze income trends by category and time period. Groups income by month or year and provides category breakdowns.
group_by (string, optional): Group by "month" or "year" (default: "month")
months (integer, optional): Number of months to analyze (default: 6)
{
"name": "analyze_income_trends",
"arguments": {
"group_by": "year",
"months": 12
}
}
Returns : Array of income trends with:
period: Time period (YYYY-MM or YYYY)
total_income: Total income for the period
transaction_count: Number of transactions
by_category: Map of category names to income amounts
get_savings_recommendationsAnalyze income vs spending and get personalized savings recommendations. Provides actionable advice based on your financial patterns.
months (integer, optional): Number of months to analyze (default: 6)
{
"name": "get_savings_recommendations",
"arguments": {
"months": 6
}
}
Returns : Savings analysis with:
period: Analysis period description
total_income: Total income for the period
total_spending: Total spending for the period
net_savings: Net savings (income - spending)
savings_rate: Savings rate as percentage
average_monthly_income: Average monthly income
average_monthly_spending: Average monthly spending
top_spending_categories: Top 5 spending categories with percentages
recommendations: Array of recommendations with:
type: "warning", "suggestion", or "positive"
title: Recommendation title
description: Detailed recommendation
priority: "high", "medium", or "low"
impact: Potential savings amount
calculate_net_worthCalculate total net worth from all accounts. Sums all account balances (assets minus liabilities).
{
"name": "calculate_net_worth",
"arguments": {}
}
Returns : Net worth calculation with:
total_assets: Sum of all positive account balances
total_liabilities: Sum of all negative account balances (as positive values)
net_worth: Total assets minus total liabilities
account_count: Number of accounts included
by_currency: Net worth broken down by currency
accounts: Array of all accounts with balances
get_financial_statsGet comprehensive financial statistics from all historical data. Provides overview metrics and yearly breakdowns.
{
"name": "get_financial_stats",
"arguments": {}
}
Returns : Financial statistics with:
total_transactions: Total number of transactions (all time)
income_transactions: Number of income transactions
expense_transactions: Number of expense transactions
total_income: Total income (all time)
total_spending: Total spending (all time)
net_savings: Net savings (all time)
average_transaction: Average transaction amount
largest_income: Largest single income transaction
largest_expense: Largest single expense transaction
account_count: Total number of accounts
category_count: Total number of categories
first_transaction_date: Date of first transaction
last_transaction_date: Date of last transaction
date_range: Formatted date range string
by_year: Map of yearly statistics with:
year: Year (YYYY)
income: Total income for the year
spending: Total spending for the year
net_savings: Net savings for the year
transaction_count: Number of transactions for the year
Database Structure This server accesses the MoneyWiz SQLite database (ipadMoneyWiz.sqlite). The database uses Core Data's entity-attribute-value model, where most objects are stored in the ZSYNCOBJECT table with different entity types (Z_ENT):
Entity 10, 11, 12, 13, 15, 16: Accounts (various types)
Entity 37, 45, 46, 47: Regular transactions
Entity 43: Transfer transactions
Entity 19: Categories
Important Notes
Dates : Transaction dates are stored as Core Data timestamps (seconds since 2001-01-01 UTC) and are automatically converted to ISO format
Balances : Account balances are stored in ZBALLANCE (note the double L). If balance is 0 or NULL, it's calculated from opening balance + transactions
Transactions : Income transactions have positive ZAMOUNT1, expense transactions have negative ZAMOUNT1
Categories : Categories are linked to transactions via the ZCATEGORYASSIGMENT table
Development
Project Structure moneywiz-mcp/
├── cmd/
│ └── main.go # Main entry point
├── internal/
│ ├── database/ # Database access layer
│ │ └── database.go
│ └── server/ # MCP server implementation
│ └── server.go
├── go.mod
└── README.md
Building go build -o moneywiz-mcp ./cmd/main.go
Validation gofmt -l .
go build ./...
go vet ./...
go test ./... -race
bash -n scripts/*.sh
Release Validation Before tagging a release:
gofmt -l .
go build ./...
go vet ./...
go test ./... -race
bash -n scripts/*.sh
Dependencies
github.com/mark3labs/mcp-go - MCP server library
github.com/mattn/go-sqlite3 - SQLite driver
License Graphify Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, e Private Gpt Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server. Scientific Agent Skills Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biolog Open Code Review Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, Codebase Memory Local code intelligence for developers and AI agents. Connect code, docs and infrastructure in a persistent graph, with CBM Lens, MCP tools, agent integrations and change-aware test selection. Orm The Prisma ORM: write your application in TypeScript with human-readable queries instead of SQL. Host your database on Prisma Postgres and your app on Prisma Compute. OpenViking Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. Context Mode Free, local plugin that keeps tool output out of your coding agent's context window. Sandbox and SQLite FTS5 search, 99% fewer bytes in context. Works with Claude Code, Codex, Pi, OMP, OpenCode, Gemin Dbx 25 MB lightweight cross-platform database client for 100+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Dock Xerj AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory a Wasp The batteries-included full-stack framework for the AI era. Develop JS/TS web apps (React, Node.js, and Prisma) using declarative code that abstracts away complex full-stack features like auth, backgr WrenAI GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data s Databases MCP 服务器 最佳 Databases MCP 服务器
暂无工具列表。远程服务器在首次健康检查后会获得工具列表。
如何安装 Moneywiz? 在本页复制适用于 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 配置。它使用发布者的安装方式,而不是 PlugMCP 代理。
Moneywiz 需要 API 密钥吗? 此记录未列出必需的环境变量。
Moneywiz 使用哪种传输方式? Moneywiz 通过 stdio 在本地运行。
Moneywiz 上次检查是什么时候? 上次检查时间:2026-10-28。 An MCP (Model Context Protocol) server for accessing MoneyWiz database data
工具
0 / 10