youtube-transcript-leads-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| APIFY_API_TOKEN | Yes | Your Apify API token. Used as the APIFY_API_TOKEN environment variable for local stdio, or as an Authorization Bearer token for the remote hosted Apify MCP Gateway. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
MCP server for extracting YouTube transcripts, timestamped RAG chunks, and verified creator business inquiry emails and sponsor links via Apify Actors. Store docs: https://apify.com/church_of_loujess/youtube-transcript-rag-scraper
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| extract_youtube_transcript_and_ragA | Extract full multi-language YouTube transcripts, timestamped chapters, metadata, and token-bounded RAG chunks with deep-links from video URLs or IDs. |
| find_youtube_channel_emailsA | Discover YouTube channels by niche keyword or @handle and extract verified business inquiry emails, sponsor links, and social handles. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools target clearly different resources and actions: one extracts transcripts/RAG chunks, the other discovers channel contact emails. There is no meaningful overlap that would cause an agent to misselect between them.
Both names use consistent snake_case with a verb-first pattern and a shared YouTube domain prefix. The structure verb_youtube_resource_outcome is predictable across the set.
Two tools are slightly below the typical 3-15 range, but each consolidates a broad, distinct workflow rather than being arbitrary. The count is reasonable for a narrowly focused transcript-and-leads server.
The surface covers the core workflows: transcript extraction with metadata/RAG chunks and channel discovery with email/social extraction. Minor gaps exist around batch operations or export/history features, but agents can work around them.