Skip to main content

Yutori MCP

MCP tools and workflow skills for building agents that operate computers as well as browse, research, and monitor the web with Yutori.

You can use it with Claude Code, Codex, Cursor, VS Code, ChatGPT, OpenClaw, and other MCP hosts.

Features

Capabilities:

  • Computer use — Operate apps on your Mac (macOS 15+)
  • Browsing — Automate websites with an AI navigator
  • Research — Run one-time deep web research tasks
  • Scouting — Monitor the web continuously for anything you care about at a desired frequency

Workflow skills (for clients that support slash commands):

Installation

Requirements

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).

AI agent install (recommended)

Paste this into Claude Code, Codex, Cursor, Windsurf, or another coding agent:

Use https://yutori.com/api/llms.txt and set up Yutori for me.

Manual quick install

MCP server installation

  1. Run in terminal:

    uvx yutori-mcp login
    

    This will open Yutori Platform in your browser and save your API key locally.

    Or, manually add your API key

    Go to (https://platform.yutori.com) and add your key to the config file:

    mkdir -p ~/.yutori
    cat > ~/.yutori/config.json << 'EOF'
    {"api_key": "yt-your-api-key"}
    EOF
    
  2. Install MCP using add-mcp (requires Node.js):

    npx add-mcp "uvx yutori-mcp"
    

    Pick the clients you want to configure.

  3. Install workflow skills using skills.sh (requires Node.js):

    npx skills add yutori-ai/yutori-mcp -g
    

    Adds slash-command shortcuts like /yutori-scout, /yutori-research, and more.

    -g installs them at user scope. Omit -g if you want a project-local install instead.

    To list or remove skills later:
    npx skills ls -g
    npx skills remove -g yutori-login
    
  4. Restart the tool you are using.

Manual per-client install

Claude Code
  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).

Claude Desktop

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.

Cursor

Click the button to install:

Install in Cursor

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.

VS Code

Click the button to install:

Install in VS Code Install in VS Code Insiders

Or install manually:

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

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

ChatGPT

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.

Codex
  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.

OpenClaw

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.
Gemini CLI

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.

Run with pip

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

pip install yutori-mcp

macOS computer use

Optional, macOS 15+ only. Computer use operates the visible desktop, or a single app window in the background while you keep working, so it needs a local driver and system permissions on top of the install above:

uvx yutori-mcp computer-use setup    # installs CuaDriver.app, requests Screen Recording + Accessibility

setup finishes by running the readiness checks and reports anything still missing. Re-run those checks any time with uvx yutori-mcp computer-use doctor.

Run a task from the terminal
uvx yutori-mcp computer-use smoke
uvx yutori-mcp computer-use run "In Calculator, compute 17 * 23 and report the result." --app Calculator
uvx yutori-mcp computer-use run "Add a note titled Standup." --app Notes --mode background

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. --mode background drives only the target app's window without taking focus, so you can keep working; add --allow-foreground-fallback to let an action that did not land in the background briefly front the window. uvx yutori-mcp computer-use stop ends the active run from another terminal (background runs have no on-screen Stop button).

The harness in this repository is minimal: one task at a time (a machine-wide lock), either on the visible desktop or targeting one app window in the background, with no multiplexing. For scalable sandbox runs, see n2 on Daytona.

Tools

See TOOLS.md for the full tool reference — computer use, Browsing, Research, and Scout tools with parameters, examples, and response formats.

Development

Setup

git clone https://github.com/yutori-ai/yutori-mcp
cd yutori-mcp
pip install -e ".[dev]"

Testing

pytest

Running locally

yutori-mcp login    # authenticate (one-time)
yutori-mcp          # run the server (or: python -m yutori_mcp.server)

Computer-use runtime

computer-use doctor verifies the pinned yutori SDK install against the published wheel. SDK contributors testing an editable checkout can override that with YUTORI_MCP_ALLOW_EDITABLE_SDK=1.

Debugging with MCP Inspector

npx @modelcontextprotocol/inspector yutori-mcp

API Documentation

For full API documentation, visit docs.yutori.com.

License

Apache 2.0

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

yutori_mcp-0.5.9.tar.gz (6.1 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

yutori_mcp-0.5.9-py3-none-any.whl (80.2 kB view details)

Uploaded Python 3

File details

Details for the file yutori_mcp-0.5.9.tar.gz.

File metadata

  • Download URL: yutori_mcp-0.5.9.tar.gz
  • Upload date:
  • Size: 6.1 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.12.14

File hashes

Hashes for yutori_mcp-0.5.9.tar.gz
Algorithm Hash digest
SHA256 97d12ea7b48c13601213de63a322d19bd96baebdc5df4eb8d952a88d368cefc2
MD5 b469b3694570e98b01b91e8ee5fde350
BLAKE2b-256 8b1f7267e7e1ec1a264983930426edf800b733ea2b2725bcc97b28c687b32b21

See more details on using hashes here.

File details

Details for the file yutori_mcp-0.5.9-py3-none-any.whl.

File metadata

  • Download URL: yutori_mcp-0.5.9-py3-none-any.whl
  • Upload date:
  • Size: 80.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.12.14

File hashes

Hashes for yutori_mcp-0.5.9-py3-none-any.whl
Algorithm Hash digest
SHA256 4c1a8812323eb3256f6372e22976cec6b380c366b8d4113347b36a81e7855b43
MD5 55fc6bfebb2b1f02f527df603601fd21
BLAKE2b-256 a5ab05305d951dc3467a17bd194d20136ccad48f41ebadc5190d868ade6dc8f4

See more details on using hashes here.

Release history Release notifications | RSS feed

0.5.12

2 files

0.5.11

2 files

This release

0.5.9 This release

2 files

0.5.8

2 files

0.5.7

2 files

0.5.6

2 files

0.5.5

2 files

0.5.4

2 files

0.5.3

2 files

0.5.2

2 files

0.5.1

2 files

0.5.0

2 files

0.3.1

2 files

0.3.0

2 files

0.2.9

2 files

0.2.8

2 files

0.2.7

2 files

0.2.6

2 files

0.2.5

2 files

0.2.4

2 files

0.2.3

2 files

0.2.2

2 files

0.2.1

2 files

0.2.0

2 files

0.1.7

2 files

0.1.6

2 files

0.1.5

2 files

0.1.4

2 files

0.1.3

2 files

0.1.2

2 files

0.1.1

2 files

0.1.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page