bookie

An MCP server that keeps books for freelancers and landlords — driven from Claude or GPT instead of QuickBooks.

Ask your LLM to import a bank statement, categorize spending, reconcile a month, or generate a Schedule C. Bookie provides the correct double-entry ledger underneath — so the model reasons over real numbers, not a spreadsheet it's improvising on the fly.

This is for you if:you're a solopreneur, freelancer, or rental property owner already living in Claude or GPT, you're comfortable with a 5-minute setup, and you want books that are actually correct.

Not for you if:you want a dashboard UI, you need multi-user access, or you're satisfied with QuickBooks / a spreadsheet.

- Node ≥ 24
- neonctl—npm install -g neonctl(freeNeonaccount; needed for the DB)
- An MCP-capable host:Claude Desktop, Claude.ai, Cursor, VS Code, or any host supporting the MCP stdio or HTTP transport

git clone https://github.com/yuens1002/bookie cd bookie npm install npm run setup # creates Neon DB, generates secrets, writes .env, runs db:push npm run build

{ "mcpServers": { "bookie": { "command": "node", "args": ["/absolute/path/to/bookie/dist/index.js"], "env": { "BOOKIE_DB_URL": "<printed by setup>", "BOOKIE_DB_DIRECT_URL": "<printed by setup>", "BOOKIE_API_KEY": "<printed by setup>" } } } }

Adding another machine to the same ledger — no clone needed:stdio is alocalprocess — every machine running a stdio MCP client spawns its own copy of the server, so each one otherwise needs its own checkout. Once the Neon DB is provisioned (vianpm run setupabove, on any one machine), everyothermachine just needs the same connection strings — nogit clone, nonpm install, nonpm run buildto keep in sync. Point that machine's MCP host at thepublished packageinstead:

{ "mcpServers": { "bookie": { "command": "npx", "args": ["-y", "bookie-mcp"], "env": { "BOOKIE_DB_URL": "<same value as your first machine>", "BOOKIE_DB_DIRECT_URL": "<same value as your first machine>", "BOOKIE_API_KEY": "<same value as your first machine>" } } } }

npxfetches and runs the published version on demand — every machine pointed at the sameBOOKIE_DB_URLshares one ledger, without any of them (besides the original) needing a checkout.

Bootstrapping a DB without cloning at all:if you don't have connection strings yet from any machine (e.g. you created the Neon project manually instead of vianpm run setup), push bookie's bundled schema directly:

mkdir bookie-mcp && cd bookie-mcp npm install bookie-mcp BOOKIE_DB_URL=<pooled> BOOKIE_DB_DIRECT_URL=<direct> npx prisma db push --schema=node_modules/bookie-mcp/prisma/schema.prisma

Then use the samenpx -y bookie-mcpconfig above.

Quick start (remote, HTTP — for Claude.ai mobile)

Railway pulls the pre-built image from GHCR — no source build needed. Set the required env vars when prompted. Seedocs/DEPLOYING.mdfor the full walkthrough (env var reference, Neon + Resend setup, Claude.ai OAuth connector).

The full, always-current tool reference lives indocs/TOOLS.md(regenerate withnpm run docs:tools). Today:

See.env.examplefor the full reference. Key variables:

- Architecture— data model, transports, layering
- Deploying— Railway + Neon + Resend setup
- Roadmap— phased plan
- Changelog— what shipped
- Releasing— versioning + release process
- Tools— generated manual
- Contributing— setup, conventions, tests

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 requires auth on every/mcprequest: either a static Bearer token (BOOKIE_API_KEY) or an OAuth JWT issued by the/tokenendpoint. Always set at least one before exposing the server beyond localhost. Seedocs/DEPLOYING.mdfor the full Claude.ai connector OAuth setup.

Financial and quantitative modeling engine for AI agents. Typed, named, deterministic.