Expense Tracker MCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Expense Tracker AI
An AI-native personal expense tracker built on the Model Context Protocol.
MCP server (FastMCP + SQLAlchemy + SQLite): expense CRUD, monthly summaries and durable memory, exposed as MCP tools, resources and prompts.
AI host (LangChain + LangGraph): an agent that discovers the server's tools and answers questions about your spending.
Streamlit UI: chat with the agent, a dashboard with charts and forms, and a memory editor — all going through the MCP server.
┌────────────────────────── AI host ──────────────────────────┐
│ Streamlit UI ──► HostRuntime ──► LangGraph agent ──► LLM │
│ (ui/) (background (host/agent.py) (OpenRouter)
│ event loop) │ │
│ └───────┬───────┘ │
│ ExpenseToolbox (one persistent │
│ MCP session, host/toolbox.py) │
└────────────────────────────┬────────────────────────────────┘
│ MCP over STDIO (subprocess)
┌────────────────────────────▼────────────────────────────────┐
│ MCP server (mcp_server/) ──► core/ (repository, schemas) │
│ │ │
│ SQLite (data/expenses.db) │
└─────────────────────────────────────────────────────────────┘Quick start
Requires Python 3.11+.
python -m venv .venv && source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -e ".[all,dev]"
cp .env.example .env # then set OPENROUTER_API_KEY
expense-tracker-ui # opens http://localhost:8501The dashboard and memory views work without an API key; only the chat needs one.
Command | What it runs |
| Streamlit UI (extra args pass through to Streamlit) |
| Terminal chat with the agent |
| The MCP server on its own, over STDIO (for any MCP host, e.g. Claude Desktop) |
Install only what you need: pip install -e . (server), .[agent] (+ agent), .[ui] (+ Streamlit).
Use the server from another MCP host
{
"mcpServers": {
"expense-tracker": {
"command": "/path/to/.venv/bin/expense-tracker-mcp",
"env": { "EXPENSE_DB_PATH": "/path/to/expenses.db" }
}
}
}Docker
docker build -t expense-tracker .
docker run -p 8501:8501 -v expense-data:/data --env-file .env expense-trackerRelated MCP server: Firmament Open Brain
Configuration
All settings are environment variables (a .env file is read automatically). See .env.example.
Variable | Default | Purpose |
|
| SQLite file |
|
| Server-side data scope (not authentication) |
|
| Log level (logs go to stderr) |
| – | Needed for chat |
|
| Any OpenRouter model id |
|
| Sampling temperature |
| current interpreter | Python used to spawn the MCP server |
MCP surface
Tools:
add_expense,list_expenses,get_expense,update_expense,delete_expense,monthly_summary,remember_preference,recall_memory,search_memoryResources:
expense://summary/{month},expense://recent,memory://all,expense://database/schemaPrompts:
monthly_spending_review,spending_coach
Project layout
src/expense_tracker/
├── config.py typed settings (pydantic-settings)
├── logging_config.py stderr logging (stdout is reserved for MCP)
├── core/ domain layer: models, schemas, repository, memory, audit
├── mcp_server/ FastMCP server (tools / resources / prompts)
├── host/ AI host: toolbox, LLM factory, agent, chat service, CLI
└── ui/ Streamlit app, async runtime bridge, formatting helpers
tests/
├── unit/ fast, no subprocesses
└── integration/ MCP server, AI host and UI (scripted LLM, no network)More detail in docs/architecture.md.
Development
make install # editable install with all extras + pre-commit hooks
make check # ruff + mypy --strict + pytest (what CI runs)
make format # auto-fixTests never call a real LLM: the agent is exercised end-to-end with a scripted chat model against a real MCP subprocess and a temporary database.
Security notes
This is a local, single-user project, not a hardened financial service.
EXPENSE_USER_IDscopes data; it is not authentication. For multi-user use, derive the owner from a verified identity and keep enforcing ownership in every query.The LLM cannot delete.
delete_expenseis hidden from the agent (DEFAULT_BLOCKED_TOOLS). The UI offers deletion to the human behind an explicit confirmation. The tool also refuses to run withoutconfirm=true.The MCP subprocess receives only
EXPENSE_*variables, so LLM keys are never passed to it.No arbitrary-SQL tool is exposed. Don't store passwords, API keys or bank details in memory items (plain text in the DB).
Never commit
.env. For production add authentication, rate limits, secret management, backups and migrations (PostgreSQL + Alembic).
License
MIT — see LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Log, query, and edit expenses, budgets, and accounts in Manilo from any MCP-compatible AI assistant.
Personal finance for AI agents — onboard, import statements, categorize & budget over MCP.
Household finance memory, budgets, transactions, and monthly reviews for AI assistants.
Log, query, and edit expenses, budgets, and accounts in Manilo (formerly Ledgy) from any MCP-compatible AI assistant.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables users to manage tasks with priorities, perform calculations with history, generate secure passwords, and analyze text, all through MCP tools, resources, and prompts.1-
- FlicenseNot gradedqualityDmaintenanceEnables each user to have a private, per-user memory store that persists across AI tools, allowing them to store, recall, search, list, and delete memories via MCP.-
- AlicenseNot gradedqualityBmaintenanceProvides persistent memory for AI agents via MCP, enabling agents to store and access notes, files, and session context across sessions and clients while under user control.4MIT

artificial-memoryofficial
AlicenseNot gradedqualityBmaintenanceEnables AI agents to persist, recall, expand, trace, and inspect durable memories with provenance through MCP tools.MIT