What does this MCP server do?
It is a minimal shell script that implements the MCP protocol and exposes a single tool named “addition” which takes two numbers and returns their sum.
@antonum
基本情報
minimalistic MCP server written in bash script
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-bash is a minimalistic MCP (Model Context Protocol) server written entirely in shell script. It implements the MCP lifecycle—initialization and operation—and provides a single tool to add two numbers, serving as a reference for learning MCP basics.
Download the mcp_add.sh script, make it executable (chmod +x mcp_add.sh), then test it from the CLI by piping JSON-RPC messages to the script (e.g., echo '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}' | bash mcp_add.sh). For use with LLM hosts, add the script’s path to a JSON configuration file under mcpServers.
It is a minimal shell script that implements the MCP protocol and exposes a single tool named “addition” which takes two numbers and returns their sum.
Pipe JSON-RPC requests directly to the script. For example, to list tools use `echo '{"method":"tools/list","id":2,"jsonrpc":"2.0"}' | bash mcp_add.sh`. To call the addition tool use `echo '{"jsonrpc":"2.0","id":20,"method":"tools/call","params":{"name":"addition","arguments":{"num1":"1","num2":"2"}}}'`.
Add an entry to the MCP configuration JSON with the command set to the full path of `mcp_add.sh` and an empty `args` array, as shown in the README.
The server requires a Unix-like environment with `bash` and optionally `jq` for formatted output during CLI testing. The script is self-contained.
No—the server provides only one tool (“addition”). It is designed as a minimal example, not a full-featured implementation.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R
MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.
Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app
JiCo for Jira & Confluence: local MCP server for Jira Data Center - redacts personal data before the AI model, holds every write for approval
コメント