Automate YouTube Operations with MCP Server
yutu is a CLI, MCP server, and AI agent that automates YouTube uploads, comments, playlists, and channel branding.
0.11.0Add to Favorites
Why it matters
Streamline and automate your YouTube channel management with the Yutu MCP Server. This tool provides a comprehensive command-line interface for interacting with various YouTube resources, enabling efficient management of videos, playlists, comments, and more.
Outcomes
What it gets done
Manage YouTube videos, playlists, channels, comments, and captions.
Automate YouTube authentication and token management.
Search for YouTube resources programmatically.
Configure and deploy as a CLI or MCP server.
Source
Get it from source
Spark does not host a copy of it.
Open sourceReports
Agent outcome reports
No reports yet
Capabilities
Tools your agent gets
List YouTube activities
Authenticate with YouTube API
Manage YouTube captions
Manage YouTube channels
Insert YouTube channel banner
Manage YouTube channel sections
Manage YouTube comments
Manage YouTube comment threads
Overview
yutu is a CLI, MCP server, and AI agent that automates YouTube workflows: uploading and optimizing videos, managing comments and playlists, and channel branding. It authenticates via Google OAuth against the YouTube Data API and exposes 35 CLI subcommands plus an agent mode with built-in SEO expertise. It can also run as an MCP server for Claude Code, Codex, VS Code, or Cursor. Use it once you have a Google Cloud project with the YouTube Data API v3 enabled and OAuth credentials set up. Skip it if you need YouTube automation without ever configuring GCP access.
What it does
yutu is a CLI, MCP server, and AI agent for YouTube (Apache 2.0 licensed) that automates the whole YouTube workflow, from uploading and optimizing videos to managing comments, playlists, channel branding, live streams, and more. The CLI alone exposes 35 subcommands covering things like video, playlist, comment, commentThread, caption, channel, channelBanner, liveBroadcast, liveChatMessage, subscription, thumbnail, and watermark, plus auth for authentication and mcp to start the MCP server. On top of the CLI, yutu ships an agent mode (nicknamed Miffy) that can retrieve, create, update, and delete YouTube content with built-in YouTube growth-strategy and SEO expertise, and a unified skill that extends other AI agents with YouTube domain knowledge across videos, playlists, comments, channels, captions, and subscriptions.
When to use - and when NOT to
Use yutu when you want to drive YouTube channel operations, video publishing, or engagement management programmatically, through an AI agent, or through an MCP-compatible client such as Claude Code, Codex, VS Code, or Cursor. It requires a Google Cloud Platform project with the YouTube Data API v3 enabled and OAuth credentials, so it is not a drop-in solution without first setting up GCP access.
Capabilities
Before anything else works, a GCP project needs YouTube Data API v3 enabled (YouTube Analytics API and YouTube Reporting API are optional), plus OAuth credentials downloaded as client_secret.json; running yutu auth --credential client_secret.json opens a browser for consent and saves the resulting token to youtube.token.json. Global environment variables YUTU_CREDENTIAL, YUTU_CACHE_TOKEN, YUTU_ROOT, and YUTU_LOG_LEVEL control credential paths, working directory, and log verbosity across every subcommand. Agent mode supports Gemini-compatible providers (default gemini-3.8-flash) and OpenAI-compatible providers such as OpenAI, DeepSeek, Ollama, and vLLM, configured with --provider, --model, --api-key, and --base-url flags, and a custom --instruction can override the built-in agent instruction.
How to install
npm i -g @eat-pray-ai/yutu
Other install paths shown in the source include Docker (docker pull ghcr.io/eat-pray-ai/yutu:latest), Go (go install github.com/eat-pray-ai/yutu@latest), a Linux/macOS install script, Homebrew (brew install yutu), Windows winget (winget install yutu), and two GitHub Actions (youtube-action, youtube-uploader) for CI use. Installed binaries can be verified with gh attestation verify against the eat-pray-ai/yutu repo. As an MCP server, yutu can be added to VS Code or Cursor via one-click badges, or registered manually in stdio mode (yutu mcp) or HTTP mode (yutu mcp --mode http) in Claude Code, Codex, or any MCP-compatible client, using YUTU_CREDENTIAL and YUTU_CACHE_TOKEN to point at the OAuth files. The YouTube skill can be added to a skills-compatible agent with npx skills add https://github.com/eat-pray-ai/yutu/tree/main/skills/youtube.
Who it's for
YouTube creators, channel managers, and teams who want to automate uploading, optimization, comment and playlist management, or channel branding, either by scripting the CLI directly, wiring an AI agent to it, or exposing it as an MCP server to an AI coding assistant.
Source README
yutu
yutu is a CLI, MCP server, and AI agent for YouTube that automates your entire YouTube workflow - from uploading and optimizing videos to managing comments, playlists, and channel branding - so you can get more views, higher click-through rates, and stronger audience engagement with less manual effort. 中文文档
Table of Contents
Prerequisites
An account on Google Cloud Platform is required. Set up the following:
Create a GCP Project and enable these APIs under
APIs & Services -> Enable APIs and services:- YouTube Data API v3 (Required)
- YouTube Analytics API (Optional)
- YouTube Reporting API (Optional)
Create OAuth credentials:
- Go to
APIs & Services -> OAuth consent screen, create a consent screen with yourself as a test user - Go to
Credentials -> Create Credentials -> OAuth Client ID, selectDesktop app - Download the credential file and save it as
client_secret.json, it should look like
{ "installed": { "client_id": "11181119.apps.googleusercontent.com", "project_id": "yutu-11181119", "auth_uri": "https://accounts.google.com/o/oauth2/auth", "token_uri": "https://oauth2.googleapis.com/token", "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs", "client_secret": "XXXXXXXXXXXXXXXX", "redirect_uris": [ "http://localhost" ] } }- Go to
Authenticate:
yutu auth --credential client_secret.jsonA browser window will open for you to grant YouTube access. After granting permission, a token is saved to
youtube.token.json.{ "access_token": "ya29.XXXXXXXXX", "token_type": "Bearer", "refresh_token": "1//XXXXXXXXXX", "expiry": "2024-05-26T18:49:56.1911165+08:00", "expires_in": 3599 }
By default, yutu will read client_secret.json and youtube.token.json from the current directory, --credential/-c and --cacheToken/-t flags are available only in auth subcommand. To modify the default path in all subcommands, set these environment variables.
Global Environment Variables
| Variable | Description | Default |
|---|---|---|
YUTU_CREDENTIAL |
Path, Base64, or JSON of OAuth client secret | client_secret.json |
YUTU_CACHE_TOKEN |
Path, Base64, or JSON of cached OAuth token | youtube.token.json |
YUTU_ROOT |
Root directory for file resolution | Current working directory |
YUTU_LOG_LEVEL |
Log level: DEBUG, INFO, WARN, ERROR |
INFO |
Installation
If you're using an AI agent, copy and paste the following prompt to finish the installation:
Install and configure yutu by following https://raw.githubusercontent.com/eat-pray-ai/yutu/refs/heads/main/internal/tools/skillgen/setup.md
You can download yutu from releases page directly, or use the following methods as you prefer.
There are two actions available for yutu, one is for general purpose and the other is for uploading video to YouTube. Refer to youtube-action and youtube-uploader for more information.
❯ npm i -g @eat-pray-ai/yutu
❯ docker pull ghcr.io/eat-pray-ai/yutu:latest
❯ docker run --rm ghcr.io/eat-pray-ai/yutu:latest
# make sure client_secret.json is in the current directory
❯ docker run --rm -it -u $(id -u):$(id -g) -v $(pwd):/app -p 8216:8216 ghcr.io/eat-pray-ai/yutu:latest
❯ go install github.com/eat-pray-ai/yutu@latest
❯ curl -sSfL https://raw.githubusercontent.com/eat-pray-ai/yutu/main/scripts/install.sh | bash
Install yutu using Homebrew🍺(recommended), or run the shell script.
❯ brew install yutu
# or
❯ curl -sSfL https://raw.githubusercontent.com/eat-pray-ai/yutu/main/scripts/install.sh | bash
❯ winget install yutu
Verify the integrity and provenance of yutu using its associated cryptographically signed attestations.
# Docker
❯ gh attestation verify oci://ghcr.io/eat-pray-ai/yutu:latest --repo eat-pray-ai/yutu
# Linux and macOS(if installed using shell script)
❯ gh attestation verify $(which yutu) --repo eat-pray-ai/yutu
# Windows
❯ gh attestation verify $(where.exe yutu.exe) --repo eat-pray-ai/yutu
Agent
yutu provides an agent mode (Miffy) to automate YouTube workflows. The agent can retrieve, create, update, and delete YouTube content, with built-in YouTube growth strategy and SEO expertise.
# Gemini(compatible) (default)
❯ yutu agent --provider google --model gemini-3.8-flash --api-key "YOUR_KEY"
❯ yutu agent --provider google --model gemini-3.8-flash --api-key "YOUR_KEY" --base-url "https://custom.endpoint.com/"
# OpenAI(compatible) (OpenAI, DeepSeek, Ollama, vLLM, etc.)
❯ yutu agent --provider openai --model gpt-5.6-terra --api-key "YOUR_KEY"
❯ yutu agent --provider openai --model deepseek-flash --api-key "YOUR_KEY" --base-url "https://api.deepseek.com/"
# web mode with sub-launchers
❯ yutu agent --args "web api a2a webui" --api-key "YOUR_KEY"
# show available launcher args
❯ yutu agent --args ""
Agent Flags
| Flag | Description | Default |
|---|---|---|
-a, --args |
Launcher arguments as a single string | console |
-p, --provider |
LLM provider: google for Gemini(compatible), openai for OpenAI(compatible) |
google |
-m, --model |
Model name | gemini-3.8-flash |
--api-key |
API key for the model provider | |
--base-url |
Base URL for the model provider's API endpoint | |
-i, --instruction |
Override the built-in agent instruction | INSTRUCTION.md |
MCP Server
Before using yutu as an MCP server, make sure yutu is installed(see Installation section), and you have a valid client_secret.json and youtube.token.json files(refer to Prerequisites section).
You can configure yutu as an MCP server for your preferred tool using the instructions below.
# Stdio mode
❯ claude mcp add --env YUTU_CREDENTIAL=/absolute/path/to/client_secret.json \
--env YUTU_CACHE_TOKEN=/absolute/path/to/youtube.token.json \
yutu -- yutu mcp
# HTTP mode (start the server first: yutu mcp --mode http)
❯ claude mcp add --transport http \
--client-id YOUR_CLIENT_ID.apps.googleusercontent.com \
--client-secret \
yutu http://localhost:8216/mcp
# Stdio mode
❯ codex mcp add --env YUTU_CREDENTIAL=/absolute/path/to/client_secret.json \
--env YUTU_CACHE_TOKEN=/absolute/path/to/youtube.token.json \
yutu -- yutu mcp
# HTTP mode (start the server first: yutu mcp --mode http)
❯ codex mcp add --url http://localhost:8216/mcp \
--oauth-client-id YOUR_CLIENT_ID.apps.googleusercontent.com \
yutu
Add the following to your MCP settings. Remember to replace the values of YUTU_CREDENTIAL and YUTU_CACHE_TOKEN with correct paths on your local machine.
{
"yutu": {
"type": "stdio",
"command": "yutu",
"args": [
"mcp"
],
"env": {
"YUTU_CREDENTIAL": "/absolute/path/to/client_secret.json",
"YUTU_CACHE_TOKEN": "/absolute/path/to/youtube.token.json"
}
}
}
Skills
yutu provides a unified skill that extends AI agents with YouTube domain knowledge, common workflows, and SEO best practices - covering videos, playlists, comments, channels, captions, subscriptions, and more.
❯ npx skills add https://github.com/eat-pray-ai/yutu/tree/main/skills/youtube
See skills/youtube/SKILL.md for the full list of supported operations.
Usage
❯ yutu
yutu is a CLI, MCP server, and AI agent for YouTube that can automate almost all YouTube workflows.
Environment variables:
YUTU_CREDENTIAL Path/Base64/JSON of OAuth client secret (default: client_secret.json)
YUTU_CACHE_TOKEN Path/Base64/JSON of cached OAuth token (default: youtube.token.json)
YUTU_ROOT Root directory for file resolution (default: current working directory)
YUTU_LOG_LEVEL Log level: DEBUG, INFO, WARN, ERROR (default: INFO)
Usage:
yutu [flags]
yutu [command]
Available Commands:
abuseReport Manage YouTube abuse reports
activity Manage YouTube activities
agent Start an agent to automate YouTube workflows
auth Authenticate with YouTube APIs
caption Manage YouTube video captions
channel Manage YouTube channels
channelBanner Manage YouTube channel banners
channelSection Manage YouTube channel sections
comment Manage YouTube comments
commentThread Manage YouTube comment threads
completion Generate the autocompletion script for the specified shell
help Help about any command
i18nLanguage Manage YouTube i18n languages
i18nRegion Manage YouTube i18n regions
liveBroadcast Manage YouTube live broadcasts
liveChatBan Manage YouTube live chat bans
liveChatMessage Manage YouTube live chat messages
liveChatModerator Manage YouTube live chat moderators
liveStream Manage YouTube live streams
mcp Start MCP server
member Manage YouTube channel members
membershipsLevel Manage YouTube membership levels
playlist Manage YouTube playlists
playlistImage Manage YouTube playlist images
playlistItem Manage YouTube playlist items
search Manage YouTube search
subscription Manage YouTube subscriptions
superChatEvent Manage YouTube Super Chat events
thirdPartyLink Manage YouTube third-party links
thumbnail Manage YouTube video thumbnails
version Show the version of yutu
video Manage YouTube videos
videoAbuseReportReason Manage YouTube video abuse report reasons
videoCategory Manage YouTube video categories
watermark Manage YouTube watermarks
Flags:
-h, --help help for yutu
Use "yutu [command] --help" for more information about a command.
Features
Please refer to FEATURES.md for more information.
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.
