mcpField
K
KBBI

KBBI

ローカル
github.com/gaato科学・教育2今日更新

KBBI について

KBBIは、公式インドネシア語辞書KBBIを検索する非公式のMCPサーバーです。単語の説明、翻訳、引用に使える構造化された項目をアシスタントに返します。

主な機能

  1. 01単語やフレーズの検索
  2. 02同形異義語と発音の取得
  3. 03語根、品詞、定義の取得
  4. 04意味付き用例の取得
  5. 05JSONリソースとして結果を提供

活用シーン

  1. 01インドネシア語の語義を確認
  2. 02語根や発音を調べる
  3. 03辞書項目を使ってフレーズを説明

MCP 対応

`kbbi_lookup`ツールと`kbbi://{query}`リソースをMCPクライアントに提供します。KBBIから項目を取得し、構造化された結果を返します。

設定

ローカルサーバーの設定はどのクライアントでも共通です。コピーしてクライアントの MCP 設定ファイルに貼り付けてください。

mcp.json · 共通設定
{
"mcpServers": {
"gaato-kbbi": {
"command": "uvx",
"args": [
"kbbi-mcp"
],
"env": {
"KBBI_TIMEOUT_SECONDS": "<KBBI_TIMEOUT_SECONDS>",
"KBBI_LOG_LEVEL": "<KBBI_LOG_LEVEL>"
}
}
}
}
起動コマンドuvx kbbi-mcp
設定が必要な環境変数
KBBI_TIMEOUT_SECONDSTimeout for each request to KBBI, in seconds.
KBBI_LOG_LEVELLevel of the server's logs, which are written to stderr.

ローカルサーバーにはマシン上の実行環境(Node.js 18 以上など)が必要です。設定ファイルの場所はクライアントごとに異なります。

パッケージ
pypikbbi-mcp0.3.0

ツール

1

掲載時のツール一覧 · 2 週間前に更新

パラメーター型必須説明
querystringはい検索する単語またはフレーズ。

README(原文)English

プロジェクトの README より

この README の日本語訳はまだありません。以下は英語の原文です。日本語の紹介はページ上部をご覧ください。

kbbi-mcp
========

.. mcp-name: io.github.gaato/kbbi-mcp

.. image:: https://img.shields.io/github/actions/workflow/status/gaato/kbbi-mcp/ci.yml?label=CI
   :target: https://github.com/gaato/kbbi-mcp/actions/workflows/ci.yml
   :alt: CI

.. image:: https://img.shields.io/pypi/v/kbbi-mcp
   :target: https://pypi.org/project/kbbi-mcp/
   :alt: PyPI

.. image:: https://img.shields.io/pypi/pyversions/kbbi-mcp
   :target: https://pypi.org/project/kbbi-mcp/
   :alt: Python

.. image:: https://img.shields.io/pypi/l/kbbi-mcp
   :target: https://github.com/gaato/kbbi-mcp/blob/HEAD/LICENSE.md
   :alt: License

.. image:: https://img.shields.io/badge/VS_Code-Install_Server-0098FF
   :target: https://insiders.vscode.dev/redirect/mcp/install?name=kbbi&config=%7B%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22kbbi-mcp%22%5D%7D
   :alt: Install in VS Code

.. image:: https://img.shields.io/badge/Cursor-Install_Server-000000?logo=cursor
   :target: https://cursor.com/en/install-mcp?name=kbbi&config=eyJjb21tYW5kIjoidXZ4IGtiYmktbWNwIn0%3D
   :alt: Install in Cursor

An MCP server that lets AI assistants look up Indonesian words in
`KBBI <https://kbbi.kemendikdasmen.go.id>`_ (Kamus Besar Bahasa Indonesia), the official Indonesian dictionary.
It returns structured entries (homographs, pronunciation, root words, word classes, definitions, and examples)
so the assistant can explain, translate, or quote them for you.

This is an **unofficial** client; see `Disclaimer`_.

Example prompts
---------------

- *What does "gemas" mean according to KBBI?*
- *Apa arti kata "mempunyai"? Apa kata dasarnya?*
- *Explain "layarnya tidak makan" using KBBI.*

Getting started
---------------

The server runs locally over stdio with `uv <https://docs.astral.sh/uv/getting-started/installation/>`_'s ``uvx``;
no API key or account is needed. Most clients accept this standard config:

.. code-block:: json

   {
       "mcpServers": {
           "kbbi": {
               "command": "uvx",
               "args": ["kbbi-mcp"]
           }
       }
   }

Claude Code
~~~~~~~~~~~

.. code-block:: bash

   claude mcp add kbbi -- uvx kbbi-mcp

Codex CLI
~~~~~~~~~

.. code-block:: bash

   codex mcp add kbbi -- uvx kbbi-mcp

Gemini CLI
~~~~~~~~~~

.. code-block:: bash

   gemini mcp add kbbi uvx kbbi-mcp

VS Code
~~~~~~~

Click the *Install in VS Code* badge at the top, or run:

.. code-block:: bash

   code --add-mcp '{"name":"kbbi","command":"uvx","args":["kbbi-mcp"]}'

Cursor
~~~~~~

Click the *Install in Cursor* badge at the top, or add the standard config to ``~/.cursor/mcp.json``
(or ``.cursor/mcp.json`` in a project).

Claude Desktop
~~~~~~~~~~~~~~

Open *Settings → Developer → Edit Config* and add the standard config to ``claude_desktop_config.json``:

- macOS: ``~/Library/Application Support/Claude/claude_desktop_config.json``
- Windows: ``%APPDATA%\Claude\claude_desktop_config.json``

Other clients
~~~~~~~~~~~~~

Use the standard config above. Without ``uv``, install the package with ``pip install kbbi-mcp`` and use
``kbbi-mcp`` (or ``python -m kbbi_mcp``) as the command.

Tools
-----

- ``kbbi_lookup``: Look up an Indonesian word or phrase in KBBI. Returns each headword with its homograph
  number, pronunciation, root words, and senses (labels such as the word class, the definition, and examples
  with their meanings). Read-only.

  - ``query`` (string, required): a word or phrase, e.g. ``makan`` or ``rumah sakit``

An empty query or a failed lookup (e.g. KBBI unreachable) is returned as a tool error. The full result
structure is published as the tool's ``outputSchema`` (``kbbi_mcp.types`` in Python).

Resources
---------

- ``kbbi://{query}``: the same result as ``kbbi_lookup``, as JSON (e.g. ``kbbi://makan``).

Configuration
-------------

Optional environment variables:

- ``KBBI_TIMEOUT_SECONDS`` (default: ``10.0``): timeout for each request to KBBI
- ``KBBI_LOG_LEVEL`` (default: ``INFO``): level of the server's logs, written to stderr
- ``KBBI_BASE_URL`` (default: ``https://kbbi.kemendikdasmen.go.id``): the KBBI site to query

For example, with Claude Code: ``claude mcp add kbbi -e KBBI_TIMEOUT_SECONDS=20 -- uvx kbbi-mcp``.
In the standard config, add an ``"env": {"KBBI_TIMEOUT_SECONDS": "20"}`` object next to ``"args"``.

Limitations
-----------

- Lookups are anonymous. KBBI shows etymology, related entries, and suggestions for missing words only to
  signed-in users, so they are not returned. When nothing is found, try the base word or another spelling.
- Each lookup fetches ``https://kbbi.kemendikdasmen.go.id/entri/{query}``. KBBI limits anonymous searches,
  so avoid rapid bulk lookups. Results are cached in memory while the server runs.
- The result depends on KBBI's page markup; if KBBI changes it, parsing may break until this package is updated.

Debugging
---------

Use the `MCP Inspector <https://github.com/modelcontextprotocol/inspector>`_:

.. code-block:: bash

   npx @modelcontextprotocol/inspector uvx kbbi-mcp

Development
-----------

With ``uv`` installed, run the server over stdio from a checkout:

.. code-block:: bash

   uv run kbbi-mcp

To point an MCP client at the checkout, use ``uv`` with ``--directory`` (an absolute path to your clone):

.. code-block:: json

   {
       "mcpServers": {
           "kbbi-dev": {
               "command": "uv",
               "args": ["--directory", "/path/to/kbbi-mcp", "run", "kbbi-mcp"]
           }
       }
   }

Checks (see ``AGENTS.md``):

.. code-block:: bash

   uv sync --frozen --group dev
   uv run ruff format .
   uv run ruff check .
   uv run ty check
   uv run pytest

Tests use saved KBBI pages in ``tests/fixtures`` and make no network requests.
Set ``KBBI_MCP_RUN_NETWORK_TESTS=1`` to also run a live smoke test.

Related projects
----------------

- `kbbi.mbt <https://github.com/gaato/kbbi.mbt>`_: a MoonBit library, CLI, and agent skill for KBBI.
  The parser and output schema of this server follow it.
- `kbbi-python <https://github.com/laymonage/kbbi-python>`_: a Python library and CLI for KBBI.

Disclaimer
----------

This project is unofficial and is not affiliated with or endorsed by the Language Development and
Cultivation Agency (Badan Bahasa) or KBBI Daring. Dictionary content belongs to its copyright holders;
see KBBI's `legal notice <https://kbbi.kemendikdasmen.go.id/Beranda/Hukum>`_. This server is meant for
personal, non-commercial lookups. You are responsible for how you use the results.

License
-------

`BlueOak-1.0.0 <https://github.com/gaato/kbbi-mcp/blob/HEAD/LICENSE.md>`_.

コメント

MCP は初めてですか?

プロトコルの概要から最初のサーバーの導入まで、よくある疑問にまとめて答えます。

AI アプリケーションが外部のツールやデータソースに統一的な方法で接続するためのオープンなプロトコルです。クライアントはモデルとの対話を担い、MCP サーバーはツール・リソース・プロンプトテンプレートを提供します。標準メッセージでやり取りするため、1 つのサーバーを複数のクライアントで再利用できます。