Fetches transcripts from YouTube videos for LLM chat apps via MCP.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@youtube-transcript-mcp Summarize https://www.youtube.com/watch?v=uB9yZenVLzg"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Transcribe YouTube videos for LLM chat apps via MCP.
Example prompt: Summarize https://www.youtube.com/watch?v=uB9yZenVLzg
Requires uv. Add this to your MCP client's config — works for any MCP-compatible app (Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, Zed, …):
{
"mcpServers": {
"youtube-transcript": {
"command": "uvx",
"args": ["youtube-transcript-mcp-server"]
}
}
}Equivalent one-liner if your client wants a single command:
uvx youtube-transcript-mcp-serverRelated MCP server: YouTube Transcript MCP Server
transcribe(youtube_video_url: str) -> str — fetches the transcript (en/de/es/fr/ru) and prepends an ad-removal instruction for the LLM.
git clone https://github.com/SeanPedersen/youtube-transcript-mcp
cd youtube-transcript-mcp
uv venv && uv pip install -r pyproject.toml && source .venv/bin/activate
python mcp_server.pyPoint your MCP client at the local checkout instead of PyPI:
{
"command": "uv",
"args": [
"run", "--with", "fastmcp", "--with", "youtube-transcript-api",
"fastmcp", "run", "/absolute/path/to/youtube-transcript-mcp/mcp_server.py"
]
}Transcribe a YouTube video using its URL.
| Name | Required | Description | Default |
|---|---|---|---|
| youtube_video_url | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries full burden. It only states the action, not behavioral traits like sync/async, output format, limits, or error handling. The minimal description leaves many unknowns.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no fluff, but it is overly terse. It is concise but not sufficiently informative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of an output schema, return values don't need explanation. However, key aspects like language support, video duration limits, or authentication are missing. The description is incomplete for a potentially complex operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% and the description only mentions 'using its URL' which maps to the parameter. No additional meaning or format details are provided beyond the parameter name.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the verb 'Transcribe' and the resource 'a YouTube video using its URL'. It is specific and unambiguous. However, with no sibling tools, differentiation is not necessary.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. No prerequisites, limitations, or context about video length, language, or availability are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0transcribeOnly one tool exists, so there is no ambiguity. The agent can only choose this tool for the transcription task.
With a single tool, naming is trivially consistent. The verb 'transcribe' clearly indicates the action.
A single tool for a video transcription service is too few. Users typically expect options for language, format, or segment selection, making this surface feel incomplete.
The tool only provides a single transcription method without any parameters for language, format, or granularity. This leaves obvious gaps in the domain coverage.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Fetch the full transcript of any YouTube video as clean text. No API key, no signup.
Clean YouTube transcripts for agents: single videos, channels, playlists, plus AI caption cleanup.
Transcribe YouTube via Whisper. Summaries, chapters, semantic-search across your corpus.
Search YouTube, read video metadata, and fetch transcripts with language preferences
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/SeanPedersen/youtube-transcript-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
