Which integrations are available for this server?

Stores and manages expense tracking data in a local SQLite database, including expense entries with categories, subcategories, dates, and amounts.

How do I use Trackor?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Trackor add a $25 lunch expense for today under food category" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Trackor

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 & Resources

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)

Dumb MCP Client

It is Dumb MCP Client meaning without any LLM (I am poor for pro) that uses MCP Server https://at0mxploit.fastmcp.app/manifest.dxt.

Remote Deployment

It is already deployed in https://dumbclient-trackor.streamlit.app/ using Streamlit Cloud.

Local Deployment

streamlit run dumb_client/app.py

MCP Server

Remote Deployment (Easiest)

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.

Local Development

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.

Go to Settings → Extensions → Advanced → Install Extension…
Select trackor-proxy.mcpb
Claude will load the MCP server via the local STDIO proxy.

This server cannot be installed

-

security - not tested

F

license - not found

-

quality - not tested

How are these scores calculated?

Resources

GitHub Repository

Need Help?

Report Issue

Related Servers

Trackor

Trackor

Tools & Resources

Dumb MCP Client

Remote Deployment

Local Deployment

MCP Server

Remote Deployment (Easiest)

Local Development

Resources

New MCP Servers

Latest Blog Posts

MCP directory API