What is the YNAB_API_TOKEN and how do I get it?
A personal access token from YNAB, obtained from https://api.ynab.com/#personal-access-tokens. It is required to use this server.
@calebl
基本情報
Model Context Protocol for YNAB (you need a budget)
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"ynab-mcp-server": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@calebl/ynab-mcp-server",
"--client",
"claude"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
A Model Context Protocol (MCP) server built with mcp‑framework that provides tools for interacting with your YNAB budgets via the YNAB API. It is designed for users who want to manage their YNAB budget through an AI conversation.
Set the required environment variable YNAB_API_TOKEN (your personal access token from YNAB) and optionally YNAB_BUDGET_ID. Configure your MCP client (e.g., Claude Desktop) with the server’s path or install it via Smithery using npx -y @smithery/cli install @calebl/ynab-mcp-server --client claude.
A personal access token from YNAB, obtained from https://api.ynab.com/#personal-access-tokens. It is required to use this server.
No. The token is stored privately in an environment variable and is never directly sent to the LLM.
The server includes ListBudgets, BudgetSummary, GetUnapprovedTransactions, CreateTransaction, and ApproveTransaction.
It is optional. If not provided, the server will prompt you to select a budget from your available budgets when you first use it.
Add a configuration entry to your Claude Desktop config file (`claude_desktop_config.json`) pointing to the server command and args, either via `npx` or local path. Instructions for both macOS and Windows are in the README.
Open-source MCP to use Blender with any LLM

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one
Hindsight: Agent Memory That Learns

Model Context Protocol Servers
コメント