by at0mxploit
Trackor — simple personal expense tracking and money management using SQLite for secure, efficient budgeting and financi
★ 3
GitHub stars
Tracks personal expenses using a SQLite database with categorization, filtering, and export capabilities. Provides comprehensive expense management through CRUD operations and financial summaries.
Trackor is a community-built MCP server published by at0mxploit that provides AI assistants with tools and capabilities via the Model Context Protocol. Trackor — simple personal expense tracking and money management using SQLite for secure, efficient budgeting and financi It is categorized under databases, finance. This server exposes 9 tools that AI clients can invoke during conversations and coding sessions.
You can install Trackor in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server supports remote connections over HTTP, so no local installation is required.
MIT
Trackor is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Enable Claude to query your database directly using natural language
Example
Ask 'Show me top 10 customers by revenue this month' and get SQL results instantly
Eliminate manual SQL writing for ad-hoc queries, get insights 10x faster
Generate complex reports and analytics without leaving conversation
Example
Analyze sales trends, cohort retention, user behavior patterns conversationally
Democratize data access—non-technical team members can query databases
Understand database structure, relationships, and data models
Example
'Explain the user_orders table schema and its relationships'
Onboard engineers faster, explore unfamiliar databases efficiently
Share your MCP server with the developer community
According to our notes, Trackor benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Trackor is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
We evaluated Trackor against two servers with overlapping tools; this profile had the clearer scope statement.
We wired Trackor into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
Trackor reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
Trackor is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
Useful MCP listing: Trackor is the kind of server we cite when onboarding engineers to host + tool permissions.
According to our notes, Trackor benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Trackor is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
Trackor has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
showing 1-10 of 31
This is a custom MCP (Model Context Protocol) server and dumb client built with FastMCP and Streamlit.
It provides tools to track expenses, including adding, listing, summarizing, updating, and exporting data.
The server uses a local SQLite database (expenses.db) and a categories.json file for expense categories.
TOOLS (callable actions that perform operations):
- add_expense : Create a new expense entry
- get_expense : Fetch a single expense by ID
- list_expenses : List expenses with optional filters
- update_expense : Modify an existing expense
- delete_expense : Remove one expense by ID
- delete_expenses_by_date_range : Remove all expenses within a date range
- summarize : Summarize expenses by category/subcategory
- get_statistics : Return overall stats and monthly breakdown
- export_expenses : Export all expenses in JSON or CSV format
RESOURCES (read-only data exposed by the server):
- expense://categories : Provides the categories.json file (list of categories/subcategories)
It is Dumb MCP Client meaning without any LLM (I am poor for pro) that uses MCP Server https://at0mxploit.fastmcp.app/manifest.dxt.
It is already deployed in https://dumbclient-trackor.streamlit.app/ using Streamlit Cloud.
streamlit run dumb_client/app.py
It is already deployed using FastMCP Cloud, you just need to drag this DXT File https://at0mxploit.fastmcp.app/manifest.dxt to Claude Extension. This automatically configures the server for Claude and includes all tools and resources. (Currently available only in Pro). It's setup for all different models and tools but I use Claude so.
Claude Connectors (remote MCP URLs) are only available for Pro users. However, non-Pro Claude Desktop users can still use this MCP server by running a local proxy.
This repository includes a proxy/ folder with a simple FastMCP STDIO bridge.
Install dependencies:
uv sync
Run MCP:
uv run main.py
Run MCP Proxy:
uv run proxy/main.py
We can also if we want use Inspector to test JSON RPC calls in MCP:
uv run fastmcp dev .\main.py
Claude Desktop no longer auto-loads raw MCP scripts.
If you're not using Claude Pro, you must install the included desktop extension:
npm install -g @anthropic-ai/mcpb
mcpb pack proxy/ trackor-proxy.mcpb
This will generate trackor-proxy.mcpb.
trackor-proxy.mcpbRun data quality queries to catch anomalies and inconsistencies
Example
Find duplicate records, missing values, orphaned foreign keys automatically
Maintain data integrity with less manual SQL work
Prerequisites
Time Estimate
15-30 minutes including configuration and testing
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
MCP server acts as bridge between Claude and database, translating natural language to SQL queries and returning results in structured format.
Protocols
Compatibility
✓ Use when
Use for ad-hoc data queries, exploratory analysis, report generation, schema exploration, and democratizing data access. Best for read-heavy analytics workloads.
✗ Avoid when
Avoid for production write operations, mission-critical transactions, real-time OLTP workloads, or when database contains sensitive PII without proper access controls. Use read replicas, not primary.