Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

YouTube Research MCP

NPM · @COYASONG/YOUTUBE-MCP-SERVER · SCANNED SEP 21

Citation-ready YouTube transcript research and optional channel intelligence for AI agents.

0 this week 84 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • Known CVEs were checked across the 160 of 161 dependencies we could resolve, so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Dependency health was assessed across the 160 of 161 dependencies we could resolve, so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency48
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 70 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability82
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1465 tokens (~104/item across 14 items; 14 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
  • Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage80
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 29% of tool parameters carry a description.Partial
  • Structured output schemas are declared (14% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 14 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the YouTube Research MCP server?

YouTube Research MCP runs locally as an npm package, launched with npx -y @coyasong/youtube-mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @coyasong/youtube-mcp-server

# add to Claude Code
claude mcp add coyasong-youtube-research -- npx -y @coyasong/youtube-mcp-server
// .cursor/mcp.json
{
  "mcpServers": {
    "coyasong-youtube-research": {
      "command": "npx",
      "args": [
        "-y",
        "@coyasong/youtube-mcp-server"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "coyasong-youtube-research": {
      "command": "npx",
      "args": [
        "-y",
        "@coyasong/youtube-mcp-server"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add coyasong-youtube-research -- npx -y @coyasong/youtube-mcp-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "coyasong-youtube-research": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@coyasong/youtube-mcp-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add coyasong-youtube-research --command npx --arg -y --arg @coyasong/youtube-mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  coyasong-youtube-research:
    command: "npx"
    args: ["-y", "@coyasong/youtube-mcp-server"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "coyasong-youtube-research": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@coyasong/youtube-mcp-server"
      ]
    }
  }
}
# add to Vellum
assistant mcp add coyasong-youtube-research -t stdio -c npx -a -y @coyasong/youtube-mcp-server
// mcp.json
{
  "mcpServers": {
    "coyasong-youtube-research": {
      "command": "npx",
      "args": [
        "-y",
        "@coyasong/youtube-mcp-server"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 15 Sept 26 0
    • Stability: 0.97 → pass security
  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Sept 2026 · Analysed npm/@coyasong/youtube-mcp-server@1.2.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 160 packages
Packages resolved 160
Deprecated 2
Stale 46
Tree resolution Partial

The dependency tree was only partially resolved, so these counts may be incomplete.

Background: SBOMs and build attestations, explained →

MCP tools · 14 exposed · ~1,465 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
analyze-channel-videos ~53

[Requires YOUTUBE_API_KEY] Analyze recent videos from a specific channel to identify performance trends

NameTypeReqDescription
channelIdstringyes
maxResultsnumber
sortBystring

No output schema declared.

No examples provided.

compare-videos ~32

[Requires YOUTUBE_API_KEY] Compare statistics for multiple YouTube videos

NameTypeReqDescription
videoIdsarrayyes

No output schema declared.

No examples provided.

enhanced-transcript ~219

Advanced transcript extraction tool with filtering, search, and multi-video capabilities. Provides rich transcript data for detailed analysis and processing. This tool offers multiple advanced features: 1) Extract transcripts from multiple videos in one request; 2) Filter by time ranges to focus on specific parts; 3) Search for specific content within transcripts; 4) Segment transcripts for structural analysis; 5) Format output in different ways (raw, timestamped, merged text); 6) Include video metadata. Parameters: videoIds (required) - Array of YouTube video IDs (up to 5); language (optional) - Language code; format (optional) - Output format ("raw", "timestamped", "merged"); includeMetadata (optional) - Whether to include video details; filters (optional) - Complex filtering options including timeRange, search, and segment.

NameTypeReqDescription
filtersobject
formatstring
includeMetadataboolean
languagestring
videoIdsarrayyes

No output schema declared.

No examples provided.

get-channel-stats ~46

[Requires YOUTUBE_API_KEY] Get statistical information for a specific YouTube channel (subscriber count, total views, video count, etc.)

NameTypeReqDescription
channelIdstringyes

No output schema declared.

No examples provided.

get-key-moments ~98

Extract concise, timestamp-linked key moments from a video transcript without returning the full transcript. Useful for quickly navigating longer videos. Parameters: videoId (required) - A YouTube video ID or URL; maxMoments (optional) - Number of key moments to extract (default: 5, max: 10).

NameTypeReqDescription
maxMomentsinteger
videoIdstringyesYouTube video ID or URL

No output schema declared.

No examples provided.

get-segmented-transcript ~147

Divide a video transcript into segments for easier analysis and navigation. This tool splits the video into equal time segments and extracts the transcript for each segment with proper timestamps. Ideal for analyzing the structure of longer videos or when you need to focus on specific parts of the content. Parameters: videoId (required) - The YouTube video ID; segmentCount (optional) - Number of segments to divide the video into (default: 4, max: 10). Returns a markdown-formatted text with each segment clearly labeled with time ranges and containing the relevant transcript text.

NameTypeReqDescription
segmentCountinteger
videoIdstringyesYouTube video ID or URL

No output schema declared.

No examples provided.

get-trending-videos ~58

[Requires YOUTUBE_API_KEY] Retrieve trending videos by region and category. This helps analyze current popular content trends.

NameTypeReqDescription
categoryIdstring
maxResultsnumber
regionCodestring

No output schema declared.

No examples provided.

get-video-categories ~34

[Requires YOUTUBE_API_KEY] Retrieve available video categories for a specific region

NameTypeReqDescription
regionCodestring

No output schema declared.

No examples provided.

get-video-comments ~67

[Requires YOUTUBE_API_KEY] Retrieve comments for a specific YouTube video with sorting options

NameTypeReqDescription
includeRepliesboolean
maxResultsnumber
orderstring
pageTokenstring
videoIdstringyes

No output schema declared.

No examples provided.

get-video-stats ~46

[Requires YOUTUBE_API_KEY] Get statistical information for a specific YouTube video (views, likes, comments, upload date, etc.)

NameTypeReqDescription
videoIdstringyes

No output schema declared.

No examples provided.

get-video-transcript ~136

Get the transcript/captions for a YouTube video with optional language selection. This tool retrieves the full transcript of a video with timestamped captions. Each caption includes the text and its timestamp in the video. Parameters: videoId (required) - The YouTube video ID; language (optional) - Language code for the transcript (e.g., "en", "ko", "ja"). If not specified, the default language for the video will be used. Returns a text with each caption line preceded by its timestamp.

NameTypeReqDescription
languagestring
videoIdstringyesYouTube video ID or URL

No output schema declared.

No examples provided.

research-video ~177

Extract a citation-ready YouTube transcript without requiring a YouTube API key. Accepts a video ID or URL and returns timestamped source links that agents can cite and open directly.

NameTypeReqDescription
contextLinesintegerNearby segments to include around query matches
endSecondsnumberOnly inspect captions at or before this time
languagestringCaption language code, for example en, ko, or ja
matchModestringWhole-word matching is the default
maxSegmentsintegerMaximum citations to return; defaults to 200
offsetintegerResult offset for pagination
querystringReturn only matching transcript segments
startSecondsnumberOnly inspect captions at or after this time
videostringyesYouTube video ID or URL
NameTypeReqDescription
citationsarrayyes
durationSecondsnumberyes
languagestringyes
matchModeyes
nextOffsetyes
offsetintegeryes
querystring|nullyes
returnedSegmentsintegeryes
sourceobjectyes
sourceUrlstringyes
timeRangeobjectyes
totalAvailableSegmentsintegeryes
totalTranscriptSegmentsintegeryes
truncatedbooleanyes
videoIdstringyes

No examples provided.

research-videos ~105

Run the same focused transcript query across 2 to 5 YouTube videos and return timestamp-linked evidence for comparison. No YouTube API key is required.

NameTypeReqDescription
contextLinesinteger
languagestringOptional caption language code
matchModestring
maxSegmentsPerVideointeger
querystringyesPhrase or word to find in every transcript
videosarrayyesYouTube video IDs or URLs
NameTypeReqDescription
querystringyes
resultsarrayyes
videosRequestedintegeryes

No examples provided.

search-videos ~247

[Requires YOUTUBE_API_KEY] Search for YouTube videos with advanced filtering options. Supports parameters: - query: Search term (required) - maxResults: Number of results to return (1-50) - channelId: Filter by specific channel - order: Sort by date, rating, viewCount, relevance, title - type: Filter by resource type (video, channel, playlist) - videoDuration: Filter by length (short: <4min, medium: 4-20min, long: >20min) - publishedAfter/publishedBefore: Filter by publish date (ISO format) - videoCaption: Filter by caption availability - videoDefinition: Filter by quality (standard/high) - regionCode: Filter by country (ISO country code)

NameTypeReqDescription
channelIdstring
maxResultsnumber
orderstring
publishedAfterstring
publishedBeforestring
querystringyes
regionCodestring
typestring
videoCaptionstring
videoDefinitionstring
videoDurationstring

No output schema declared.

No examples provided.

Common questions

What is the YouTube Research MCP server?

YouTube Research MCP is listed in the public MCP registry as io.github.coyaSONG/youtube-research. Citation-ready YouTube transcript research and optional channel intelligence for AI agents. This page covers its npm package (@coyasong/youtube-mcp-server).

Is the YouTube Research MCP server safe to use?

YouTube Research MCP scores 84 out of 100 on VerifyMCP. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the YouTube Research MCP server expose?

YouTube Research MCP exposes 14 tools: search-videos, get-video-comments, research-video, research-videos, get-video-transcript, and 9 more. Their descriptions and schemas cost roughly 1,465 tokens of context every time the server is loaded.

Is the YouTube Research MCP server still maintained?

YouTube Research MCP is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the YouTube Research MCP server under?

YouTube Research MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.