Koskamo

YouTube MCP

The YouTube MCP server provided by Wondel.ai enables AI agents to search for YouTube videos, channels, playlists, and movies. It allows fetching detailed video information including related videos, comments, and replies. Additionally, it can retrieve full transcripts for any available language, including auto-generated captions, converting video content into readable text for agents.

Visit Wondel.ai

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

YouTube MCP logo, by Wondel.aiVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-02Operated by Wondel.ai
MCP endpoint (Streamable HTTP)
https://mcp.wondel.ai/youtube/mcp
Vendor documentation

What its tools do

3 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (3)

3 of 3 have a description · 0 of 3 declare behavior hints · 3 of 3 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to wondel.ai ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Search YouTube for videos, channels, playlists, and movies based on a query.
  • Fetch detailed video information, including related videos and comments.
  • Retrieve full transcripts of videos in various languages, including auto-generated captions.

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: ai.wondel/youtube@1.0.0Project website

Protocol and capabilities

Server
YouTube 1.0.0
MCP protocol negotiated in check
2025-06-18
Tools
3 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Tools

3 advertised

youtube_search — Search YouTube (SerpAPI)
Advertised by the server during the last successful anonymous check.

Search YouTube live via SerpAPI. Returns video_results (videos), plus channels, playlists, movies and related searches. Each video result's id is the YouTube video id — feed it as `v` to youtube_video (details, related videos, comments) and to youtube_transcript. `sp` carries SerpAPI filter and next-page tokens from a prior result for pagination / refined filtering.

youtube_search input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "search_query"
  ],
  "properties": {
    "gl": {
      "type": "string",
      "maxLength": 2,
      "minLength": 2,
      "description": "Country code for the search, e.g. 'us', 'uk', 'de'."
    },
    "hl": {
      "type": "string",
      "description": "Language code, e.g. 'en', 'es', 'pt-br'."
    },
    "sp": {
      "type": "string",
      "description": "Filter / pagination token from a prior result: carries YouTube search filters and the next-page token."
    },
    "no_cache": {
      "type": "boolean",
      "description": "Force a fresh SerpAPI fetch and bypass this server's result cache. Default false."
    },
    "zero_trace": {
      "type": "boolean",
      "description": "Enterprise-only ZeroTrace mode: don't store search params/metadata on SerpAPI. Default false."
    },
    "search_query": {
      "type": "string",
      "description": "Search query for YouTube (required). Same syntax as the YouTube search box."
    }
  }
}
youtube_video — Get YouTube Video (SerpAPI)
Advertised by the server during the last successful anonymous check.

Fetch a single YouTube video by id via SerpAPI: details, related videos, comments and replies. `v` is the video id from a youtube_search video_results entry. Page related videos / comments / replies with next_page_token from a prior result.

youtube_video input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "v"
  ],
  "properties": {
    "v": {
      "type": "string",
      "description": "YouTube video id (required), e.g. the id from a youtube_search video_results entry."
    },
    "gl": {
      "type": "string",
      "maxLength": 2,
      "minLength": 2,
      "description": "Country code for the search, e.g. 'us', 'uk', 'de'."
    },
    "hl": {
      "type": "string",
      "description": "Language code, e.g. 'en', 'es', 'pt-br'."
    },
    "no_cache": {
      "type": "boolean",
      "description": "Force a fresh SerpAPI fetch and bypass this server's result cache. Default false."
    },
    "zero_trace": {
      "type": "boolean",
      "description": "Enterprise-only ZeroTrace mode: don't store search params/metadata on SerpAPI. Default false."
    },
    "next_page_token": {
      "type": "string",
      "description": "Token from a prior result to page through related videos, comments, or replies."
    }
  }
}
youtube_transcript — Get YouTube Transcript (SerpAPI)
Advertised by the server during the last successful anonymous check.

Fetch a YouTube video's transcript via SerpAPI. `v` is the video id from a youtube_search result. Pick a track with language_code (default 'en' — use the video's own language), and optionally title and type ('asr' for auto-generated captions). When the requested track doesn't exist the tool falls back once to an available track (same language first, manual before auto-generated) and says so in `note`.

youtube_transcript input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "v"
  ],
  "properties": {
    "v": {
      "type": "string",
      "description": "YouTube video id (required) — the id from a youtube_search result."
    },
    "type": {
      "type": "string",
      "description": "Transcript track type: 'asr' for auto-generated captions; omit for manual captions. If that track doesn't exist, an available one is used instead and `note` says which."
    },
    "title": {
      "type": "string",
      "description": "Transcript track title to select when multiple tracks exist."
    },
    "no_cache": {
      "type": "boolean",
      "description": "Force a fresh SerpAPI fetch and bypass this server's result cache. Default false."
    },
    "zero_trace": {
      "type": "boolean",
      "description": "Enterprise-only ZeroTrace mode: don't store search params/metadata on SerpAPI. Default false."
    },
    "language_code": {
      "type": "string",
      "description": "Transcript language code, e.g. 'en', 'pl'. Default 'en' — pass the video's own language. If that track doesn't exist, an available one is used instead and `note` says which."
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (4 of 4 answered).

  1. 2026-11-02: 3 of 3 checks answered
  2. 2026-11-03: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
211 ms
95th percentile latency
211 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 211 ms · metadata changed · 3 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http youtube-mcp-wondel https://mcp.wondel.ai/youtube/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add youtube-mcp-wondel --url https://mcp.wondel.ai/youtube/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable youtube-mcp-wondel in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "youtube-mcp-wondel": {
      "url": "https://mcp.wondel.ai/youtube/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "youtube-mcp-wondel": {
      "type": "streamableHttp",
      "url": "https://mcp.wondel.ai/youtube/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start youtube-mcp-wondel and inspect its tools.
VS Code configuration
{
  "servers": {
    "youtube-mcp-wondel": {
      "type": "http",
      "url": "https://mcp.wondel.ai/youtube/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http youtube-mcp-wondel https://mcp.wondel.ai/youtube/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "youtube-mcp-wondel": {
      "url": "https://mcp.wondel.ai/youtube/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "youtube-mcp-wondel": {
      "serverUrl": "https://mcp.wondel.ai/youtube/mcp"
    }
  }
}

Let your agent find its tools

Find servers like YouTube MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 4,469

Do you run YouTube MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing