What can MCP Server - Build Tools do?
It exposes Maven build tools through MCP, allowing users to build projects using natural language instead of remembering exact Maven commands.
@thepragmatik
基本情報
An Model Context Protocol based Server for build tools for the JVM.
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": {
"maven-tools": {
"command": "<path-to-java-home-directory>/bin/java",
"args": [
"-jar",
"-Dmaven.home=<path-to-maven-home-directory>",
"<path-to-the-mcp-maven-server.jar>"
]
}
}
}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。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
MCP Server - Build Tools is a Model Context Protocol server that lets users interact with Apache Maven using natural language. It is designed for developers who want a simple, intuitive way to invoke Maven builds without remembering specific plugins, goals, or arguments.
Install by adding the server to your MCP client configuration (e.g., Claude Desktop). Use the provided JSON block to specify the Java executable, Maven home, and the JAR file path. Restart the client, then submit build tasks in natural language.
It exposes Maven build tools through MCP, allowing users to build projects using natural language instead of remembering exact Maven commands.
Currently only Apache Maven is supported. Future support for other build tools is possible if there is interest.
You need Java 21 or later, Maven installed, and an MCP client such as Claude Desktop or Goose. A local LLM is optional if using Goose.
Edit the `claude_desktop_config.json` file (on macOS at `~/Library/Application Support/Claude/claude_desktop_config.json`) to add the server configuration with paths to Java, Maven home, and the JAR file. Restart Claude.
No internet or API keys are mentioned; the server runs locally using your own Maven installation and Java runtime.

Agent-Native Terminal

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

Launch your product from your AI agent. Connect Claude Code, Codex, Cursor or ChatGPT to Launchdog over MCP and your agent drafts the listing, picks a launch week and books it. 50 launches a week, ranked only by human vo
コメント