yutu runs on your own machine — the client starts it, so there is no endpoint to ping. 177 installs a week from npm. Last commit 5 Nov 2026.
CLI, MCP server, and AI agent to automate YouTube workflows
We read the source, 1 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
dir := filepath.Join(baseDir, t.subdir)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add yutu -e 'YUTU_CREDENTIAL=<YUTU_CREDENTIAL>' -e 'YUTU_CACHE_TOKEN=<YUTU_CACHE_TOKEN>' -- npx -y @eat-pray-ai/yutu
{
"mcpServers": {
"yutu": {
"command": "npx",
"args": [
"-y",
"@eat-pray-ai/yutu"
],
"env": {
"YUTU_CACHE_TOKEN": "<YUTU_CACHE_TOKEN>",
"YUTU_CREDENTIAL": "<YUTU_CREDENTIAL>"
}
}
}
}
[mcp_servers.yutu]
command = "npx"
args = ["-y", "@eat-pray-ai/yutu"]
env = { YUTU_CREDENTIAL = "<YUTU_CREDENTIAL>", YUTU_CACHE_TOKEN = "<YUTU_CACHE_TOKEN>" }
{
"mcpServers": {
"yutu": {
"command": "npx",
"args": [
"-y",
"@eat-pray-ai/yutu"
],
"env": {
"YUTU_CACHE_TOKEN": "<YUTU_CACHE_TOKEN>",
"YUTU_CREDENTIAL": "<YUTU_CREDENTIAL>"
}
}
}
}
{
"servers": {
"yutu": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@eat-pray-ai/yutu"
],
"env": {
"YUTU_CACHE_TOKEN": "<YUTU_CACHE_TOKEN>",
"YUTU_CREDENTIAL": "<YUTU_CREDENTIAL>"
}
}
}
}
Put your own values in place of
<YUTU_CREDENTIAL> (GCP project credential for yutu, Base64 encoded JSON or path to JSON file), <YUTU_CACHE_TOKEN> (YouTube authentication token, Base64 encoded JSON or path to JSON file).
The author’s registry entry marks them as required.
Optional settings from the registry entry, left out of the block above:
YUTU_LOG_LEVEL (Log level).
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Connect AI agents to Blog2Social and automate social media content workflows via MCP.
MCP server for n8n workflow management -- view, create, sync and manage workflows via AI.
MCP server for n8n workflow management -- view, create, sync and manage workflows via AI.
Command wrapper MCP server for coding agents, compression, workflows, and local automation.
MCP server for browser automation with AI agent
Raycast workflow automation MCP server with 9 tools
MCP server for browser automation via Vercel's agent-browser CLI
Answers built from our own checks of this server.