OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
MCP & Tooling

YouTube MCP Server

YouTube MCP Server is a Python Model Context Protocol server that exposes tools for searching YouTube videos, retrieving transcripts, storing video information and transcripts in a vector database, and semantically searching stored transcripts.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

YouTube MCP Server — OpenViST project profile in MCP & Tooling.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when an MCP client needs YouTube video discovery and transcript-based research, especially when you want to search a collection of stored transcripts.

Who it is for

  • Developers connecting YouTube research tools to an MCP-compatible assistant.
  • Researchers who want to collect video transcripts and search them by topic or meaning.

Documented uses

  • Search YouTube videos using a query.
  • Retrieve a transcript from a video URL.
  • Store video information and its transcript in a vector database.
  • Search stored transcripts semantically.
Before you choose

Requirements & limits

The project is a public GitHub repository with an MIT license. Its documented setup requires a Google API key for embeddings.

  • The tool is a server to connect to an MCP client, not a standalone assistant.
  • Semantic search operates on transcripts stored in the vector database.
  • The README lists Python 3.8+, uv, and a Google API key for embeddings as prerequisites.
  • The project states that YouTube search does not use the official YouTube API.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the server for an MCP client

Install the Python project and configure it to start as an MCP server.

Before you start

  • Python 3.8 or later
  • uv package manager
  • Google API key for embeddings

Steps

  1. Clone the repository and create and activate a virtual environment with uv.

  2. Install dependencies with the command below.

    Documented command
    uv pip install -r requirements.txt

  3. Add the Google API key to a .env file.

  4. Start the server with the command below, or configure the server entry in Claude Desktop settings.

    Documented command
    uv run python server.py

Expected outcome

The server is set up to expose its YouTube tools to an MCP client; the README gives Claude Desktop as an example.

Guide limitations

  • This guide covers setup and startup; it does not verify a successful client connection.
  • The documented Claude Desktop configuration examples use Windows paths.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
YouTube MCP ServerSearch YouTube videos using a query.ServerThe project is a public GitHub repository with an MIT license. Its documented setup requires a Google API key for embeddings.
Smart Connections MCP ServerSearch vault notes by natural-language meaning rather than exact keywords.CLI, Self-hostedThe README documents local installation and configuration with Claude Code and a vault path. It describes no hosted service or account flow.
Milvus SkillCreate and manage Milvus collections, schemas and indexes.CLI, Cloud, Self-hostedThe repository is public and licensed under Apache-2.0. Its documented installation method adds the skill to Claude Code.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
IA-Programming/Youtube-MCP · Official homepage title · retained in its source language
How we review sourcesSuggest a correction