bookie
A Model Context Protocol (MCP) server that keeps the books for your personal and business finances using double-entry accounting — driven entirely from an LLM.
README
bookie
A Model Context Protocol (MCP) server that keeps the books for your personal and business finances using double-entry accounting — driven entirely from an LLM. No UI: Claude or GPT is the interface.
Import bank-statement CSVs, categorize spending (including photographed receipts), reconcile monthly, and generate US Schedule C tax reports — by asking your assistant. Runs locally over stdio or remotely over HTTP so a mobile consumer LLM can reach it.
Why no UI?
The host LLM already reads CSVs, sees receipt images, and writes prose. Bookie owns the things an LLM shouldn't improvise: a correct double-entry ledger, integer-cent money math, deterministic categorization rules, and reproducible reports. The model handles language and vision; the server handles the books.
Quick start (local, stdio)
npm install # also runs `prisma generate`
cp .env.example .env # then fill in BOOKIE_DB_URL / BOOKIE_DB_DIRECT_URL (Neon)
npm run db:push # apply schema to your Neon database
npm run dev # starts on stdio; seeds the default chart on first run
Register it with Claude Desktop (claude_desktop_config.json). Point BOOKIE_DB_URL at your one shared Neon DB — the same value the deployed HTTP server uses — so local and mobile share one ledger:
{
"mcpServers": {
"bookie": {
"command": "node",
"args": ["C:/Users/yuens/dev/bookie/dist/index.js"],
"env": {
"BOOKIE_DB_URL": "postgresql://USER:PASSWORD@ep-xxxx-pooler.REGION.aws.neon.tech/neondb?sslmode=require"
}
}
}
}
(Run npm run build first, or point command at npx/tsx for dev.)
Quick start (remote, HTTP — for mobile LLMs)
npm run build
BOOKIE_TRANSPORT=http BOOKIE_API_KEY=$(openssl rand -hex 32) npm start
# Streamable HTTP endpoint: POST http://localhost:3000/mcp
# Health check: GET http://localhost:3000/health
Deploy to Railway with the included Dockerfile / railway.json (the start command runs prisma db push then boots). Set BOOKIE_API_KEY (clients send Authorization: Bearer <key>) and point BOOKIE_DB_URL + BOOKIE_DB_DIRECT_URL at your Neon Postgres production branch — the same DB your local server uses. Every instance reads and writes the one and only ledger; there is no local copy to reconcile.
Tools
The full, always-current tool reference lives in docs/TOOLS.md (regenerate with npm run docs:tools). Today:
| Tool | What it does |
|---|---|
manage_accounts |
Create/list/archive accounts (personal vs business; Schedule C lines) |
add_transaction |
Record one balanced double-entry (money flows from → to) |
query_transactions |
List entries + postings by date range / account |
account_balances |
Current balance per account |
More — CSV import, categorization rules, receipts, reconciliation & tax reports, email delivery — are on the roadmap.
Configuration
See .env.example. Key variables: BOOKIE_TRANSPORT, BOOKIE_DB_URL (+ BOOKIE_DB_DIRECT_URL), BOOKIE_API_KEY, RESEND_API_KEY.
Docs
- Architecture — data model, transports, layering
- Roadmap — phased plan
- Changelog — what shipped
- Tools — generated manual
- Contributing — setup, conventions, tests
Safety
Bookie stores financial data in your Neon Postgres database; connection strings live in .env (gitignored) and Railway env vars — never commit them. The HTTP transport is open unless BOOKIE_API_KEY is set — always set it before exposing the server beyond localhost.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.