Tubescout MCP Server

by not0lucky Your server? Claim it

local only

Tubescout runs on your own machine — the client starts it, so there is no endpoint to ping. 34 installs a week from npm. Last commit 27 Aug 2026.

YouTube as a research engine: keyless search, video intel, resilient transcripts, demand signals.

Installs per day peak 16 · avg 6 · -10% w/w

a month agotoday

Installs / week

npm · tubescout

Stars

0 open issues

27 Aug 2026

Last commit

2 releases in 90 days

MIT

License

TypeScript

Nothing serious here today

Today is the operative word: we check Tubescout every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

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 Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add tubescout -- npx -y tubescout

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "tubescout": {
      "args": [
        "-y",
        "tubescout"
      ],
      "command": "npx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.tubescout]
command = "npx"
args = ["-y", "tubescout"]

.cursor/mcp.json

{
  "mcpServers": {
    "tubescout": {
      "args": [
        "-y",
        "tubescout"
      ],
      "command": "npx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "tubescout": {
      "args": [
        "-y",
        "tubescout"
      ],
      "command": "npx"
    }
  }
}

Alternatives to Tubescout

same job, measured the same way

HasData YouTube

by hasdata

Search YouTube and read video, channel and transcript data as JSON. No Google Cloud project.

313 installs/wk 4 tools answering

Google & YouTube Search, Transcripts and Data - FlashData

by flashdata-dev

Google & YouTube data: search, news, images, shopping, places, transcripts, captions and downloads.

answering

Web Search

by hec-ovi

Keyless multi-engine web search, fetch, and clean-Markdown read for AI agents. No API keys.

142 installs/wk local only

Patents Trademarks IP MCP Server

by thenextgennexus

Patent & trademark IP search — patents, assignees, and inventors via Google Patents.

4 tools answering

Vexor

by scarletkc

A semantic search engine for files and code.

443 installs/wk local only

AIsa SERP — Other Engines

by aisa

Search results outside Google: Bing, Yahoo, Baidu, Naver, Seznam and YouTube.

answering

VARRD — Statistically Validated Trading Edges + AI Research Engine

by augiemazza

Validated trading edges across futures, equities, crypto. Live signals, full audit trail.

9 tools answering

Ransack

by chancewalker165-dot

Web search & fetch MCP for AI agents: 12 engines, one key, flat $15/mo at ransack.tools.

answering

Tubescout — questions

Answers built from our own checks of this server.

Why is there no uptime for Tubescout?

Tubescout runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package tubescout was installed 34 times last week.

How do I connect Tubescout?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls tubescout straight from npm; nothing to host, nothing to sign up for.

How many people use Tubescout?

The npm package tubescout was installed 34 times in the last week. Week over week that is -10%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Tubescout open source?

Yes — it is published under the MIT licence, written in TypeScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.