mcp_server_for_claudes_toolbox
@the-ride-never-ends
关于 mcp_server_for_claudes_toolbox
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.).
基本信息
配置
工具
未检测到工具
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is mCP_Server_For_Claudes_Toolbox?
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.
How to use mCP_Server_For_Claudes_Toolbox?
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.
Key features of mCP_Server_For_Claudes_Toolbox
- Arbitrary function registration and invocation – add functions to
tools/functions - Exposes CLI tools: test_generator, documentation_generator, lint_a_python_codebase, run_tests_and_save_their_results, codebase_search
- Each CLI tool can have its own virtual environment
- Customizable server settings via
configs.yaml(verbosity, log level, host, port, reload) - Cross‑platform support for WSL2, Linux/MacOS, and Windows
Use cases of mCP_Server_For_Claudes_Toolbox
- Generate unittest test files from JSON specifications
- Create markdown documentation from Python source code
- Fix common linting issues (blank lines, trailing spaces, newlines) in Python files
- Run unit tests, type checking, and linting for Python projects and save results as JSON and Markdown
- Search codebases with pattern matching
FAQ from mCP_Server_For_Claudes_Toolbox
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.
What are the system requirements for mCP_Server_For_Claudes_Toolbox?
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.
Where is the server configured?
Customizable settings like verbosity, log level, host, port, and reload options are stored in the configs.yaml file.
How does the server work under the hood?
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.
How do I connect the server to Claude Desktop or Copilot?
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.
开发工具 分类下的更多 MCP 服务器
sentry-mcp
getsentryAn MCP server for interacting with Sentry via LLMs.
Serena
oraiosA powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
MCP-Bridge
SecretiveShellA middleware to provide an openAI compatible endpoint that can call MCP tools
OpenSumi
opensumiA framework helps you quickly build AI Native IDE products. MCP Client, supports Model Context Protocol (MCP) tools via MCP server.

Sentry
modelcontextprotocolModel Context Protocol Servers
评论