Trackor
Trackor is a custom MCP server and simple client built on FastMCP and Streamlit, providing an expense tracking tool that supports functions such as addition, deletion, modification, query, statistical summarization, and export. It uses an SQLite database and a JSON classification file.
2.5 points
6.0K

What is Trackor?

Trackor is an intelligent expense tracking assistant that seamlessly integrates with AI assistants (such as Claude) through the MCP protocol. It allows you to use natural language to record, query, and analyze your daily expenses. The system automatically categorizes your expenses and provides detailed statistical reports.

How to use Trackor?

You can use Trackor in two ways: 1) Use it directly in Claude Desktop (Pro version required), 2) Use it in non - Pro Claude through a local proxy, 3) Use the independent Web interface (Streamlit client). In any case, you can interact with the expense tracking system using natural language.

Use Cases

Trackor is very suitable for scenarios such as personal financial management, team reimbursement tracking, and project budget monitoring. Whether you want to track personal daily expenses or manage team reimbursement records, Trackor can provide a convenient solution.

Main Features

Intelligent Expense Recording
Use natural language to add expense records, and the system automatically parses the amount, date, and category information.
Multi - Dimensional Filtering and Querying
Supports filtering and querying expense records by multiple conditions such as date range, category, and amount.
Visual Statistical Analysis
Provides expense summaries by category and sub - category, and generates monthly statistical reports and trend analyses.
Data Export Function
Supports exporting expense data in JSON or CSV format for further analysis or backup.
Batch Operation Support
Supports batch deletion of expense records within a specified date range to improve management efficiency.
Multi - Platform Access
Provides three access methods: Claude integration, Web interface, and local proxy to meet the needs of different users.
Advantages
Completely free and open - source, no subscription fees required
Data is stored locally to protect privacy and security
Seamlessly integrated with AI assistants, allowing natural language interaction
Supports multiple deployment methods, flexible and convenient
Provides comprehensive expense management functions
Open - source project, with customizable and extensible functions
Limitations
Only Claude Pro users can directly use the remote MCP server
Non - Pro users need to configure a local proxy
Basic command - line operation knowledge is required for local deployment
Currently only supports the SQLite database
The Web interface has relatively basic functions

How to Use

Choose a Usage Method
Choose the most suitable usage method according to your needs: Claude Pro users can directly use the remote server, non - Pro users need to configure a local proxy, or use the Web interface.
Claude Pro Users (Easiest)
In Claude Desktop, drag the DXT file to the extension area to complete the configuration.
Non - Pro User Configuration
Install dependencies and run the local proxy server, then install the MCP extension.
Use the Web Interface
Access the online Web interface or run the Streamlit application locally.
Start Using
Interact with Trackor using natural language to record and query your expenses.

Usage Examples

Daily Expense Recording
Record various daily expenses such as dining, transportation, and shopping every day.
Monthly Budget Analysis
Analyze expenses in each category at the end of each month to evaluate budget implementation.
Team Reimbursement Management
Manage team members' reimbursement applications and approval records.
Project Cost Tracking
Track expenses related to a specific project to control the project budget.
Tax Preparation
Organize deductible business expenses to prepare for tax filing.

Frequently Asked Questions

Do I need Claude Pro to use Trackor?
Where is my data stored? Is it safe?
How can I back up my expense data?
Can I customize expense categories?
Does it support multi - user or multi - device synchronization?
How can I get help if I encounter technical problems?
Is Trackor free?
Do I need programming knowledge to use it?

Related Resources

Online Web Interface
The Trackor interface that can be used directly in the browser without installation.
MCP Server Configuration
Direct configuration link for Claude Pro users.
GitHub Repository
Project source code and complete documentation.
FastMCP Documentation
Official documentation and tutorials for the FastMCP framework.
MCP Protocol Specification
Official technical specification of the Model Context Protocol.
Claude Desktop
Download and installation guide for the Claude Desktop client.

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

A
Airweave
Airweave is an open - source context retrieval layer for AI agents and RAG systems. It connects and synchronizes data from various applications, tools, and databases, and provides relevant, real - time, multi - source contextual information to AI agents through a unified search interface.
Python
15.1K
5 points
V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
9.4K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
8.9K
4.5 points
F
Finlab Ai
FinLab AI is a quantitative financial analysis platform that helps users discover excess returns (alpha) in investment strategies through AI technology. It provides a rich dataset, backtesting framework, and strategy examples, supporting automated installation and integration into mainstream AI programming assistants.
8.7K
4 points
H
Haiku.rag
Haiku RAG is an intelligent retrieval - augmented generation system built on LanceDB, Pydantic AI, and Docling. It supports hybrid search, re - ranking, Q&A agents, multi - agent research processes, and provides local - first document processing and MCP server integration.
Python
16.9K
5 points
M
Maverick MCP
MaverickMCP is a personal stock analysis server based on FastMCP 2.0, providing professional level financial data analysis, technical indicator calculation, and investment portfolio optimization tools for MCP clients such as Claude Desktop. It comes pre-set with 520 S&P 500 stock data, supports multiple technical analysis strategies and parallel processing, and can run locally without complex authentication.
Python
11.8K
4 points
C
Cipher
Cipher is an open-source memory layer framework designed for programming AI agents. It integrates with various IDEs and AI coding assistants through the MCP protocol, providing core functions such as automatic memory generation, team memory sharing, and dual-system memory management.
TypeScript
0
5 points
C
Contracts Wizard
OpenZeppelin Contracts Wizard is an interactive smart contract building tool that allows users to generate contract code based on OpenZeppelin components by selecting contract types, parameters, and functions. It supports multiple programming languages and provides API and embedding functions.
TypeScript
11.7K
4 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
39.0K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
23.7K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
81.2K
4.3 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
28.2K
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
69.4K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
38.3K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
24.9K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
55.1K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase