Skip to main content
Glama
PraveenKishore

YouTube Transcript MCP Server

by PraveenKishore
OverviewSchemaRelated ServersScoreDiscussions
Remote

YouTube Transcript MCP Server

This project implements a Model Context Protocol (MCP) server that provides a tool for fetching YouTube video transcripts in various formats. Leveraging the youtube-transcript-api, the server allows Large Language Models (LLMs) to access YouTube transcripts securely and efficiently.

Overview

The server exposes a tool, fetch_youtube_transcript, which retrieves transcripts for YouTube videos based on the provided video ID, language code, and desired format. This functionality enables LLMs to access and process YouTube video transcripts seamlessly.

Related MCP server: YouTube Transcript Server

Features

  • YouTube Transcript Retrieval: Fetch transcripts for YouTube videos in multiple languages.

  • Flexible Output Formats: Obtain transcripts in either plain text or JSON format.

  • MCP Integration: Designed to work seamlessly with MCP-compatible clients and tools.

Configuration with MCP Client

"mcpServers": {
  "youtube-transcripts": {
    "command": "uv",
    "args": [
      "--directory",
      "/ABSOLUTE/PATH/TO/PARENT/FOLDER/mcp-transcripts/src",
      "run",
      "server.py"
    ]
  }
}

Setup

This project uses uv for package/project management. To run this project, follow the below setup instructions.

  1. Install uv if you haven't already. Here's the installation instructions.

  2. Clone the repo.

    git clone https://github.com/PraveenKishore/mcp-server-youtube.git
cd mcp-server-youtube

  3. Create virtual env and install dependencies.

    uv sync

  4. Activate the virtual env.

    source .venv/bin/activate  # Activate the virtual environment (Linux/MacOS)
# OR
.\.venv\Scripts\activate  # Activate the virtual environment (Windows)

  5. You're all set!

Testing the MCP Server

1. Testing Only the MCP Server

To launch the MCP inspector, run the following command:

mcp dev src/server.py

This will start the server, allowing you to view the list of exposed tools in the Tools tab. You can also invoke any of these tools with the appropriate input.

2. Testing with Claude Desktop

To test with Claude Desktop, add the MCP configuration to the claude_desktop_config.json file.
For more details, refer to this link. Once configured, you should be able to invoke the tool directly within the Claude Desktop interface.

3. Testing with mcp-client-cli

The mcp-client-cli is a simple command-line tool for running LLM prompts and implementing the Model Context Protocol (MCP) client.
To use this tool, add the MCP configuration to ~/.llm/config.json. For further setup instructions, check out the official setup guide. After configuration, you’ll be able to invoke the tool within mcp-client-cli.

Available Tools

1 tool
fetch_youtube_transcriptB

Tool to fetch the transcript of a YouTube video.

:param video_id: The unique identifier of the YouTube video. :param lang_code: The language code for the transcript (default is 'en' for English). :param format: The desired output format of the transcript; either 'text' or 'json'. :return: The transcript in the specified format.

ParametersJSON Schema
NameRequiredDescriptionDefault
video_idYes
lang_codeNoen
formatNojson

TDQS

B3.4/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It does not mention side effects, auth requirements, rate limits, or error behavior (e.g., invalid video_id). Only parameter and return description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is concise: one-line summary then parameter list. The docstring format adds slight verbosity, but front-loads the purpose and is well-organized.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers input parameters adequately but lacks details on output format structure (e.g., JSON fields) and error handling. With no output schema, description should provide more return value context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, but description explains each parameter: video_id, lang_code (default 'en'), format ('text' or 'json'). Adds meaning beyond schema titles, though could specify accepted lang codes or valid format values more explicitly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'fetches the transcript of a YouTube video,' with a specific verb and resource. No sibling tools exist, so differentiation is not an issue.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives, no prerequisites, limitations, or context for when not to use it. It only describes what it does.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0
Disambiguation5/5

Only one tool exists, so there is no risk of confusion between tools. The tool's purpose is clearly defined.

Naming Consistency5/5

With a single tool, naming consistency is inherent. The name 'fetch_youtube_transcript' uses clear snake_case and is descriptive.

Tool Count3/5

A single tool for fetching YouTube transcripts is appropriate for a focused service, but the tool surface is minimal and may be considered thin for broader use cases.

Completeness4/5

The tool covers the primary function of fetching transcripts with language and format options. No additional operations like listing or searching are expected for a transcript-only server, so gaps are minor.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/PraveenKishore/mcp-server-youtube'

If you have feedback or need assistance with the MCP directory API, please join our Discord server