What does Beancount MCP do?
It lets an MCP host (like Claude Desktop) run Beancount queries and add transactions to your ledger.
@StdioA
基本情報
A MCP Server for beancount query and transaction submmit.
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": {
"github": {
"command": "uvx",
"args": [
"beancount-mcp",
"/path/to/your/ledger.bean"
],
"env": {}
}
}
}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。
Beancount MCP is a Model Context Protocol server that enables AI assistants to execute queries and submit transactions to a Beancount ledger.
Run uvx beancount-mcp [--transport=stdio/sse] your_ledger.bean to start the server. For Claude Desktop, add an entry to claude_desktop_config.json specifying the command and path to your ledger.
It lets an MCP host (like Claude Desktop) run Beancount queries and add transactions to your ledger.
Install it via the `uvx` tool. No separate install step is mentioned; run `uvx beancount-mcp` directly.
You can use `--transport=stdio` (default) or `--transport=sse` for HTTP streaming.
You need `uvx` and a Beancount ledger file. No additional dependencies are listed.
The server reads from the ledger file you specify on the command line. Data is not stored by the server itself.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

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
不止于 CSS

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
コメント