ynab-mcp
Enables reading and writing YNAB budget data, such as listing budgets, accounts, categories, transactions, and creating or updating transactions, through natural language commands.
README
ynab-mcp
An MCP server that exposes your YNAB (You Need A Budget) budget to MCP clients such as Claude Desktop and claude.ai.
Tools
Read
ynab_list_budgets— budgets accessible with your tokenynab_list_accounts— accounts and balances of a budgetynab_list_categories— category groups with budgeted / activity / balanceynab_list_payees— payees (paginated)ynab_list_transactions— transactions with filters (account, category, date, type)ynab_get_budget_month— monthly summary (to-be-budgeted, income, activity, age of money)
Write
ynab_create_transaction— create a transaction (amount in currency units, negative = expense)ynab_update_transaction— partially update a transaction (categorize, approve, memo…)
Requirements
- uv
- A YNAB Personal Access Token — YNAB → Account Settings → Developer Settings → New Token
Setup
uv sync # install dependencies
cp .env.example .env # then put your token in .env
.env:
YNAB_TOKEN=your-token-here
YNAB_BUDGET_ID= # optional; empty = use YNAB's "last-used" budget
Run it:
uv run ynab-mcp
Use with Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"ynab": {
"command": "uv",
"args": ["run", "--directory", "/absolute/path/to/ynab-mcp", "ynab-mcp"],
"env": { "YNAB_TOKEN": "your-token-here" }
}
}
}
Remote (HTTP) hosting
Set MCP_TRANSPORT=http to serve over streamable-http (endpoint /mcp):
MCP_TRANSPORT=http HOST=0.0.0.0 PORT=8000 uv run ynab-mcp
Deploy to FastMCP Cloud
This server is built with the fastmcp package, so
it deploys as-is on FastMCP Cloud:
- Push this repo to GitHub, then connect it as a project on fastmcp.cloud.
- Set the entrypoint to
src/ynab_mcp/server.py:mcp. - Add
YNAB_TOKEN(and optionallyYNAB_BUDGET_ID) as an environment variable/secret in the project settings — dependencies are picked up automatically frompyproject.toml.
You can validate the entrypoint locally first:
uv run fastmcp inspect src/ynab_mcp/server.py:mcp
Conventions
- Amounts are in normal currency units; an expense is negative (e.g.
-12.50). Conversion to/from YNAB milliunits is automatic. budget_iddefaults toYNAB_BUDGET_ID, or the"last-used"budget if unset.- YNAB rate limit: 200 requests / hour / token.
Development
uv sync --extra dev
uv run pytest # tests (HTTP mocked, no network)
uv run ruff check . # lint
Security
Never commit .env — it contains a live token and is gitignored. If a token
leaks, rotate it in YNAB's Developer Settings.
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.