youtube-research-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| YOUTUBE_API_KEY | No | YouTube Data API v3 key for search and comments functionality. Optional; without it, only transcript and channel analysis are available. | |
| YOUTUBE_RESEARCH_CACHE_DB | No | Custom path for the SQLite cache database file. If not set, uses default OS-specific path. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_transcriptC | Fetch a YouTube transcript by URL or video ID. |
| search_videosC | Search YouTube videos and return structured metadata. |
| get_video_commentsC | Fetch top-level YouTube comments for one video. |
| collect_video_discussionC | Collect one video's transcript plus comments for discussion analysis. |
| collect_research_sourcesC | Search YouTube and collect transcript-ready sources for analysis. |
| collect_research_discussionsC | Search YouTube and collect transcript plus comments for each usable video. |
| analyze_videosC | Collect transcripts, metadata, and optional comments for specific videos. |
| analyze_channelC | Collect transcripts and comments from a specific YouTube channel's recent videos. |
| get_quota_usageA | Return today's YouTube Data API quota usage and remaining estimate. |
| get_capabilitiesA | Return which tools are available based on current configuration. |
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 10 tools
Several tools have overlapping purposes, such as analyze_channel, analyze_videos, collect_research_discussions, collect_research_sources, and collect_video_discussion, all dealing with transcripts and comments. This could confuse an agent about which tool to use.
Tool names use a mix of verbs (analyze, collect, get, search) and the verb_noun pattern is not consistently applied. For example, 'analyze_channel' and 'analyze_videos' are similar but 'get_capabilities' and 'search_videos' follow a different pattern.
With 10 tools, the server covers a reasonable scope for YouTube research without being overly complex. The count is appropriate for the domain.
The tool set covers the core workflow of searching, fetching transcripts and comments, and analyzing channels. Minor gaps exist, such as missing direct channel metadata retrieval or playlist support, but overall it is fairly complete.