What configuration file does mcp-tools-cli use?
It uses a JSON file named `mcp_config.json` by default, which must contain a `mcpServers` object defining the command, arguments, and environment variables for each MCP server.
@moritalous
基本情報
command-line client for interacting with Model Context Protocol (MCP) servers.
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": {
"time": {
"command": "python",
"args": [
"-m",
"mcp_server_time",
"--local-timezone=America/New_York"
]
}
}
}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-tools-cli is a command-line client for interacting with Model Context Protocol (MCP) servers. It allows users to list available tools on a configured MCP server and call those tools directly from the terminal.
Install it via pip install mcp-tools-cli. Create a mcp_config.json file (or use --config-path) with server definitions under mcpServers. Then run commands like mcp-tools-cli list-tools --mcp-name <name> or mcp-tools-cli call-tool --mcp-name <name> --tool-name <tool>.
--config-path.It uses a JSON file named `mcp_config.json` by default, which must contain a `mcpServers` object defining the command, arguments, and environment variables for each MCP server.
Two actions are available: `list-tools` to list the tools provided by a given MCP server, and `call-tool` to invoke a specific tool with optional arguments.
Use the `--tool-args` option. It accepts a JSON string (e.g., `'{"key":"value"}'`) or a plain string. If the string is not valid JSON, it is automatically passed as the `query` argument to the tool.
The client prints a `ValueError` message indicating the MCP server name was not found in the configuration file.
Yes, a sample file `mcp_config.sample.json` is included in the package, configured for the Time MCP Server. To use it, install `mcp-server-time` first.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP


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