What runtime does linux-mcp-server require?
Java 17+ and Maven 3.6+ (or the bundled Maven wrapper). The target hosts must have SSH service enabled.
@MartinDai
基本情報
support execute shell on a remote linux or local machine
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。
A Model Context Protocol (MCP) server built with Spring Boot and Spring AI that executes shell commands on local or remote Linux hosts. It exposes an executeShell tool via the MCP standard interface, allowing AI assistants like Claude Desktop to perform command-line operations securely.
src/main/resources/hosts.json to configure remote host credentials (IP, username, password).mvn spring-boot:run or package it as a JAR (mvn clean package; java -jar target/linux-mcp-server-1.0.0.jar). The server listens on port 3001 at /mcp.executeShell tool, which accepts machineIp (optional), path (optional), and shell (required) parameters.hosts.json.mvn spring-boot:run or executable JAR.Java 17+ and Maven 3.6+ (or the bundled Maven wrapper). The target hosts must have SSH service enabled.
Credentials are stored in plain text inside `hosts.json`. The README advises against committing production credentials; use environment variables or a secure config store for sensitive environments.
No. It uses `PromiscuousVerifier` which skips host key verification. For production, replace with a known‑hosts list to prevent man‑in‑the‑middle attacks.
The server uses STREAMABLE HTTP transport and listens on port `3001` at the `/mcp` endpoint. Both can be changed in `application.yml`.
SSH connections are cached by Caffeine with a default idle timeout of 5 minutes. The cache duration and maximum size can be adjusted in `RemoteShellService`.
🚀 The fast, Pythonic way to build MCP servers and clients.
A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
Open-source MCP to use Blender with any LLM
コメント