yt-mcp
MCP ServerFreeMCP server: yt-mcp
Capabilities7 decomposed
youtube metadata extraction via mcp protocol
Medium confidenceExposes YouTube video and channel metadata through the Model Context Protocol, allowing AI clients to query video titles, descriptions, durations, upload dates, and channel information without direct YouTube API calls. Implements MCP resource and tool endpoints that translate client requests into YouTube data retrieval operations, abstracting authentication and API rate-limiting complexity behind a standardized protocol interface.
Implements YouTube integration as a first-class MCP server rather than a library or plugin, enabling seamless integration with MCP-native clients like Claude Desktop without requiring custom client-side code or API management
Provides standardized MCP protocol access to YouTube data, making it compatible with any MCP client ecosystem rather than being locked to a specific framework or platform
mcp resource publication for video/channel data
Medium confidencePublishes YouTube videos and channels as MCP resources with standardized URIs and content types, allowing MCP clients to discover and reference YouTube data as first-class resources in the protocol. Uses MCP resource listing and retrieval endpoints to expose video/channel information with consistent schemas, enabling clients to treat YouTube content as persistent, queryable resources rather than one-off API responses.
Treats YouTube videos and channels as first-class MCP resources with discoverable URIs and standardized schemas, rather than exposing them only through tool/function calls, enabling resource-based workflows and knowledge indexing
Enables MCP clients to browse and reference YouTube content as persistent resources, providing better discoverability and context persistence than tool-call-only approaches
mcp tool/function calling for youtube queries
Medium confidenceExposes YouTube search and metadata operations as callable MCP tools with JSON schema definitions, allowing AI clients to invoke YouTube queries as part of agentic workflows. Implements tool definitions with input schemas (video ID, search terms, filters) and output schemas (metadata objects), enabling LLMs to decide when and how to query YouTube data as part of reasoning chains without explicit client-side orchestration.
Implements YouTube operations as declarative MCP tools with JSON schemas, enabling LLM-driven tool selection and chaining rather than requiring explicit client-side orchestration of YouTube queries
Allows LLMs to autonomously decide when to query YouTube as part of reasoning, providing better integration with agentic workflows than passive resource-only approaches
youtube api credential abstraction and management
Medium confidenceAbstracts YouTube API authentication (API key or OAuth) behind the MCP server, eliminating the need for clients to manage credentials directly. The server handles credential storage, token refresh, and rate-limit tracking, exposing a clean MCP interface that clients use without knowledge of underlying authentication mechanisms. Implements credential validation and error handling to provide consistent authentication behavior across all YouTube operations.
Centralizes YouTube API credential management at the MCP server level rather than distributing credentials to clients, providing a single point of control for authentication and quota management
Eliminates credential distribution complexity and security risks by keeping API keys server-side, compared to approaches that require clients to manage credentials independently
youtube video metadata retrieval with structured output
Medium confidenceFetches detailed video metadata (title, description, duration, upload date, view count, channel info) from YouTube and returns it as structured JSON objects with consistent schemas. Implements YouTube Data API v3 integration with response parsing and field mapping, transforming raw API responses into normalized metadata objects that MCP clients can reliably consume and process.
Provides normalized, schema-consistent video metadata output through MCP, abstracting YouTube API response parsing and field mapping complexity from clients
Returns structured, validated metadata objects rather than raw API responses, reducing client-side parsing complexity and enabling reliable downstream processing
youtube channel metadata and video listing
Medium confidenceRetrieves channel-level metadata (channel name, description, subscriber count, video count) and lists videos from a channel with pagination support. Implements YouTube Data API v3 channel and playlist endpoints, handling pagination tokens and result filtering to enable clients to browse channel content systematically without managing API pagination complexity.
Abstracts YouTube channel and video listing APIs behind MCP tools, handling pagination and result normalization so clients can browse channel content without managing API pagination tokens
Provides transparent pagination handling and normalized channel/video listings through MCP, compared to raw API approaches that require clients to manage pagination state
youtube search with result ranking and filtering
Medium confidenceImplements YouTube search functionality through MCP, accepting search queries and returning ranked video results with optional filtering by upload date, duration, and relevance. Translates search queries into YouTube Data API v3 search requests, applying result ranking and filtering logic to surface the most relevant videos without requiring clients to implement search ranking algorithms.
Exposes YouTube search as an MCP tool with built-in result ranking and filtering, enabling LLMs to autonomously search for relevant videos without managing search API complexity
Provides ranked, filtered search results through MCP, compared to raw search APIs that return unranked results requiring client-side filtering and ranking logic
Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.
Related Artifactssharing capabilities
Artifacts that share capabilities with yt-mcp, ranked by overlap. Discovered automatically through the match graph.
Advanced YouTube
A Model Context Protocol (MCP) server for interacting with YouTube data. This server provides resources and tools to query YouTube videos, channels, comments, and transcripts through a stdio interface.
YouTube Data Server
Provide token-optimized, structured YouTube data to enhance your LLM applications. Access efficient tools for video search, detailed metadata retrieval, transcript fetching, channel analysis, and trend discovery. Reduce token consumption and improve performance with AI-tailored data formats.
YouTube MCP Server
Extract and analyze YouTube video transcripts via MCP.
Mcptube – Karpathy's LLM Wiki idea applied to YouTube videos
I watch a lot of Stanford/Berkeley lectures and YouTube content on AI agents, MCP, and security. Got tired of scrubbing through hour-long videos to find one explanation. Built v1 of mcptube a few months ago. It performs transcript search and implements Q&A as an MCP server. It got traction
youtube
MCP server: youtube
youtube-transcript-mcp-server
MCP server: youtube-transcript-mcp-server
Best For
- ✓AI developers building MCP-native agents that need YouTube integration
- ✓Teams using Claude Desktop or other MCP clients who want YouTube data access
- ✓Builders prototyping LLM workflows that analyze video metadata at scale
- ✓MCP client developers building resource-aware interfaces
- ✓Teams implementing MCP resource discovery and browsing UIs
- ✓Builders creating knowledge management systems that treat YouTube as a resource layer
- ✓AI developers building agentic systems with tool-use capabilities
- ✓Teams implementing LLM-driven YouTube analysis workflows
Known Limitations
- ⚠Requires running yt-mcp as a separate server process — adds deployment complexity vs direct library usage
- ⚠YouTube API quota limits apply; no built-in caching or rate-limit optimization documented
- ⚠Limited to metadata extraction — cannot download video content, transcripts, or comments without additional implementation
- ⚠MCP protocol overhead adds latency compared to direct synchronous API calls
- ⚠Resource discovery performance depends on YouTube API pagination — large channel listings may be slow
- ⚠No built-in caching of resource metadata — repeated queries hit YouTube API each time
Requirements
Input / Output
UnfragileRank
UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.
Repository Details
About
MCP server: yt-mcp
Categories
Alternatives to yt-mcp
Search the Supabase docs for up-to-date guidance and troubleshoot errors quickly. Manage organizations, projects, databases, and Edge Functions, including migrations, SQL, logs, advisors, keys, and type generation, in one flow. Create and manage development branches to iterate safely, confirm costs
Compare →AI-optimized web search and content extraction via Tavily MCP.
Compare →Scrape websites and extract structured data via Firecrawl MCP.
Compare →Are you the builder of yt-mcp?
Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.
Get the weekly brief
New tools, rising stars, and what's actually worth your time. No spam.
Data Sources
Looking for something else?
Search →