What is the difference between global and project installation scopes?
Global installations are shared across projects and stored in `~/.roo/mcps`, while project installations are specific to the current directory and stored in `./.roo/mcps`.
@robertheadley
基本信息
An MCP server installer for Roo Code. Handles the installation from Github, requirements, package management, update, installation and MCP Json configuration.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"Roo-Code-MCP-installer": {
"command": "python",
"args": [
"roo.py",
"install",
"username/my-cool-mcp"
]
}
}
}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。
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。
A command-line utility that streamlines installing and managing Roo Model Context Protocol (MCP) servers. It fetches MCP server code from Git repositories, handles dependencies, configuration, and registration within the Roo environment.
Run the script with python roo.py <command> [options]. Use install <repo_input> to install an MCP, optionally with --scope global|project or --skip-env. Use list to show installed MCPs, and logs to view log files with options like --lines and --follow.
user/repo slugs.Global installations are shared across projects and stored in `~/.roo/mcps`, while project installations are specific to the current directory and stored in `./.roo/mcps`.
Python 3.11 or higher and Git must be installed. Additional tools (Node.js/npm, Python/pip, Go, Rust/Cargo) are needed depending on the MCP server’s project type.
Yes, use the `--demo` flag with the `install` command to see the UI and intended actions without modifying the file system or running commands.
Use the `--skip-env` flag when running the `install` command to skip the interactive prompt for required environment variables.
Rust project support is still in progress and may not work correctly.

Compliance frameworks delivered to AI agents. Nizh gives your agent read access to your organization's compliance program — SOC 2, ISO 27001, CMMC 2.0, NIST, and more — as MCP tools, so it can check posture, read a contr

Nebelus is an enterprise agentic-AI platform for regulated industries. This MCP server exposes the Nebelus Construction API: ~48 tools that give an MCP client full agent build parity — create/update/probe agents, edit ag

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

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.
评论