What is the Dev-Kit MCP Server?
It is an MCP server that provides file, Git, and Makefile operations within a restricted root directory, intended for use with AI agent development tools and editors like VS Code.
@DanielAvdar
基本信息
Agent development tool-kit
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"dev-kit-mcp-server": {
"command": "uvx",
"args": [
"dev-kit-mcp-server",
"--root-dir",
"${workspaceFolder}"
],
"env": {}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
Dev-Kit MCP Server is a Model Context Protocol (MCP) server designed for agent development tools, enabling secure, scoped file and Git operations within a designated root project directory. It is built for integration with AI-assisted development environments like VS-Code Copilot.
Install with pip install dev-kit-mcp-server. Run the server using dev-kit-mcp-server --root-dir=workdir, optionally specifying a custom TOML file for predefined commands with --commands-toml=custom_commands.toml. The server exposes tools such as file operations, Git operations, Makefile execution, text/file search, and predefined command execution.
It is an MCP server that provides file, Git, and Makefile operations within a restricted root directory, intended for use with AI agent development tools and editors like VS Code.
All file and directory operations are confined to the root directory specified by the `--root-dir` parameter, preventing access to files outside of that scope.
The server provides file creation/move/rename/removal, Git status/add/commit/push/pull/checkout/diff, Makefile target execution, file and text search, predefined command execution, and line-range reading.
It requires Python (see PyPI badge for versions) and is installed via pip: `pip install dev-kit-mcp-server`. No other runtime dependencies are listed.
Run `dev-kit-mcp-server --root-dir=workdir` from the command line. Optionally add `--commands-toml=<file>.toml` to use custom predefined commands.

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Open-source MCP to use Blender with any LLM

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
评论