If you don't already have uv installed, install it (it includes uvx):

curl -LsSf https://astral.sh/uv/install.sh | sh

Or with Homebrew:

brew install uv

Python 3.10 or higher is required (uv manages this automatically for most installs).

For the quickstart below, Node.js is also required (for npx).

1. Plugin (Recommended) - Includes MCP tools + workflow skills

   Type these commands in Claude Code's input (not in a terminal):

   /plugin marketplace add yutori-ai/yutori-mcp
   /plugin install yutori@yutori-plugins
   

   This installs both the MCP tools and workflow skills:

   Skill	Description
   /yutori-computer-use	Local Mac desktop automation
   /yutori-browse	Browser automation tasks
   /yutori-research	Deep web research workflow (async, 5-10 min)
   /yutori-scout	Set up continuous web monitoring with comprehensive queries
   /yutori-competitor-watch	Quick competitor monitoring template
   /yutori-api-monitor	API/changelog monitoring template

   Already have the MCP server installed? Remove it first to avoid duplicate configurations:

   claude mcp remove yutori -s user   # if installed at user scope
   claude mcp remove yutori -s local  # if installed at local/project scope
   

   To uninstall the plugin later:

   /plugin uninstall yutori@yutori-plugins -s user
   

2. MCP Only (if you prefer not to use the plugin)

   claude mcp add --scope user yutori -- uvx yutori-mcp
   

   The server reads your API key from ~/.yutori/config.json (set up via uvx yutori-mcp login).

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "yutori": {
      "command": "uvx",
      "args": ["yutori-mcp"]
    }
  }
}

The server reads your API key from ~/.yutori/config.json.

For setup details, see the Claude Desktop MCP install guide.

Click the button to install:

Or install manually:

Go to Cursor Settings → MCP → Add new MCP Server, then add:

{
  "mcpServers": {
    "yutori": {
      "command": "uvx",
      "args": ["yutori-mcp"]
    }
  }
}

The server reads your API key from ~/.yutori/config.json.

See the Cursor MCP guide for setup details.

Click the button to install:

Or install manually:

code --add-mcp '{"name":"yutori","command":"uvx","args":["yutori-mcp"]}'

The server reads your API key from ~/.yutori/config.json.

Open ChatGPT Desktop and go to Settings -> Connectors -> MCP Servers -> Add server.

{
  "mcpServers": {
    "yutori": {
      "command": "uvx",
      "args": ["yutori-mcp"]
    }
  }
}

The server reads your API key from ~/.yutori/config.json.

For setup details, see the OpenAI MCP guide.

1. MCP Server:

   codex mcp add yutori -- uvx yutori-mcp
   

   Or add to ~/.codex/config.toml:

   [mcp_servers.yutori]
   command = "uvx"
   args = ["yutori-mcp"]
   

   The server reads your API key from ~/.yutori/config.json.

2. Skills (optional, for workflow guidance):

   Install skills using $skill-installer inside Codex:

   $skill-installer install https://github.com/yutori-ai/yutori-mcp/tree/main/.agents/skills/yutori-computer-use
   $skill-installer install https://github.com/yutori-ai/yutori-mcp/tree/main/.agents/skills/yutori-browse
   $skill-installer install https://github.com/yutori-ai/yutori-mcp/tree/main/.agents/skills/yutori-research
   $skill-installer install https://github.com/yutori-ai/yutori-mcp/tree/main/.agents/skills/yutori-scout
   $skill-installer install https://github.com/yutori-ai/yutori-mcp/tree/main/.agents/skills/yutori-competitor-watch
   $skill-installer install https://github.com/yutori-ai/yutori-mcp/tree/main/.agents/skills/yutori-api-monitor
   

   Or manually copy skills to your user directory (use -L so symlinks are dereferenced and real files are copied):

   git clone https://github.com/yutori-ai/yutori-mcp /tmp/yutori-mcp
   cp -rL /tmp/yutori-mcp/.agents/skills/* ~/.agents/skills/
   

   To uninstall manually copied skills, delete the matching directories from ~/.agents/skills/. When updating this way, remove old Yutori skill directories first, since cp -rL will not delete renamed or removed skills.

   Restart Codex after installing skills.

   Skill	Command	Description
   Computer Use	$yutori-computer-use	Local Mac desktop automation
   Browse	$yutori-browse	Browser automation with AI navigator
   Research	$yutori-research	Deep web research (async, 5-10 min)
   Scout	$yutori-scout	Set up continuous web monitoring
   Competitor Watch	$yutori-competitor-watch	Quick competitor monitoring template
   API Monitor	$yutori-api-monitor	API/changelog monitoring template

   See the Codex Skills docs for more on skills.

Follow the Quickstart above:

1. Install skills and MCP for OpenClaw (and optionally other tools) via skills.sh:

   npx skills add yutori-ai/yutori-mcp
   

   When prompted, choose which Yutori skills to install and select OpenClaw as the tool.

Add to ~/.gemini/settings.json. If you already have mcp or mcpServers, merge these keys into your existing config:

{
  "mcp": {
    "allowed": ["yutori"]
  },
  "mcpServers": {
    "yutori": {
      "command": "uvx",
      "args": ["yutori-mcp"]
    }
  }
}

The server reads your API key from ~/.yutori/config.json.

Add "yutori" to mcp.allowed if you already list other MCPs there. For more details, see the Gemini CLI MCP settings guide.

Install the package to run the MCP server (e.g. for custom or self-hosted setups):

pip install yutori-mcp

uvx yutori-mcp computer-use smoke
uvx yutori-mcp computer-use run "In Calculator, compute 17 * 23 and report the result." --app Calculator

smoke is an end-to-end check: it types into Calculator to confirm the permissions took effect, then has the agent compute 9 * 9 in Calculator. run does whatever task you give it, printing each action as the agent takes it.