What models does Lazy Terminal support?
It supports multiple language models via Coagent integration; you configure credentials in `models.yaml`.
@Heterohabilis
基本情報
An LLM-based smart terminal for lazy guys :P
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": {
"Lazy_Terminal": {
"command": "python",
"args": [
"main.py"
]
}
}
}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。
Lazy Terminal is an intelligent command-line assistant that connects language models with external tools through the Modular Component Protocol (MCP). It dynamically determines whether a query should be directly answered or passed to a registered tool, enabling seamless terminal automation and smart interaction.
Install dependencies with pip install -r requirements.txt, edit config/models.yaml to add model credentials and config/mcp_servers.yaml to list MCP servers, set required API keys as environment variables, then launch the assistant with python main.py.
It supports multiple language models via Coagent integration; you configure credentials in `models.yaml`.
Edit `config/models.yaml` for model credentials and `config/mcp_servers.yaml` for MCP server definitions, then set corresponding API keys as environment variables.
Yes, Lazy Terminal runs only safe, controlled bash scripts through its MCP tools.
It maintains context by default for the last 50 interactions.
Python with packages listed in `requirements.txt`; install via `pip install -r requirements.txt`.

TestMu AI MCP Server lets developers run, debug, and triage tests through natural language directly from their IDE (Cursor, Claude, GitHub Copilot, and other MCP clients). It exposes five tools — HyperExecute (test orche

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

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

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.
コメント