How do I add a new tool to mCP_Server_For_Claudes_Toolbox?
Just add a function to the `tools/functions` folder, name the file after the function, and it will be available for use.
@the-ride-never-ends
基本情報
A server application that exposes CLI programs and functions via the Model Context Protocol (MCP), making them accessible to AI assistants through different interfaces (Claude Code, Claude Desktop, Copilot, etc.).
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_For_Claudes_Toolbox is a server application that exposes Claude’s Toolbox utility programs via the Model Context Protocol (MCP), making them accessible to AI assistants like Claude through interfaces such as Claude Code, Claude Desktop, and Copilot. It is authored by Claude 3.7 Sonnet and Kyle Rose, version 0.2.0.
Clone the repository, run the installation script (install_server.sh on Linux/MacOS or install_server.bat on Windows), then copy the appropriate platform‑specific MCP config code into the relevant MCP configuration file (e.g., claude_desktop_config.json for Claude Desktop on Windows). Optionally, clone the individual CLI tool repositories into the claude_toolbox/tools/cli directory. Integrated applications call the server via the MCP protocol; the server starts automatically when the configured command is executed.
tools/functionsconfigs.yaml (verbosity, log level, host, port, reload)Just add a function to the `tools/functions` folder, name the file after the function, and it will be available for use.
Python 3.12+ is required, along with the dependencies listed in the installation (mcp, aiofile, anthropic, flask, duckdb, etc.). Currently WSL2 and Linux are supported; Windows support is forthcoming.
Customizable settings like verbosity, log level, host, port, and reload options are stored in the `configs.yaml` file.
The server runs tools through subprocess calls to the command line, using a wrapper function that activates the appropriate virtual environment for each tool. Each tool is exposed with its parameters via the MCP protocol.
Copy the platform‑specific JSON configuration block (e.g., for WSL, Linux, or Windows) into the relevant MCP config file. For Claude Desktop on Windows, the file is typically at `C:\Users\<username>\AppData\Roaming\Claude\claude_desktop_config.json`.

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

Pugi is an AI product team that builds, checks and publishes websites and apps. Its MCP server gives agents a passive website security check graded A+ to F (headers, TLS, cookies, exposed keys in scripts), free with a no

Give an agent a place to put large output. Instead of returning 40k characters of a build log into the conversation, it posts the file to DocBin and hands back one short URL. Docs render with syntax highlighting and mark
Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up
コメント