About tubedata
tubedata is a local bridge for retrieving public YouTube data as JSON, for applications and workflows that need search results, video or channel details, or transcripts. It forwards requests to HasData’s hosted MCP server and supports CLI and stdio MCP access.
Key features
- 01Search videos, channels, and Shorts
- 02Fetch video details and timed transcripts
- 03Retrieve channel pages and tabs
- 04Filter and paginate search results
- 05CLI and stdio MCP modes
Use cases
- 01Find YouTube videos on a topic
- 02Review details and transcript for a video
- 03Inspect a channel’s content and subscriber count
MCP support
Exposes YouTube search, video, channel, and transcript tools to MCP clients through a local server, forwarding calls to HasData’s hosted MCP server. It also supports CLI invocation.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
4Saved tool list · updated 2d ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| gl | string | No | The two-letter country code for the country you want to limit the search to. Provide one exact documented value (245 allowed), e.g. `ac`, `af`. |
| hl | string | No | The two-letter language code for the language you want to use for the search. Provide one exact documented value (159 allowed), e.g. `af`, `ak`. |
| tab | enum | No | Channel tab to scrape. Each tab returns a different content shape: - `featured` (default) — channel Home page (channel trailer + curated rows) - `videos` — uploaded long-form videos - `shorts` — Shorts feed - `streams` — past and upcoming live streams - `playlists` — created and saved playlists - `posts` / `community` — community posts - `podcasts` — podcast episodes - `releases` — music releases - `about` — channel description, links, stats - `store` — channel merchfeatured | videos | shorts | streams | playlists | posts | community | podcasts | releases | about | store |
| channelId | string | Yes | YouTube channel identifier — either the canonical channel ID (`UC…`, 24 chars) or the public handle starting with `@` (e.g. `@PewDiePie`). Legacy `/c/<custom>` and `/user/<name>` URL slugs are also accepted. |
| deviceType | enum | No | Device type for the request.desktop | mobile |
| paginationToken | string | No | Token returned in the previous response to fetch the next page of results. |
Details
From the project READMEtubedata
tubedata is a small local bridge to the hosted HasData YouTube MCP server, which returns YouTube data as JSON. Ask it for a search query and it returns the results page split into videos, channels, Shorts, shelves and ads; give it one video ID and it fetches that video's full details or its timed transcript; give it a channel ID or handle and it fetches that channel's page, tab by tab.
The bridge keeps no YouTube data of its own. It serves the upstream server's tool list locally, exactly as captured from the live endpoint, and forwards each tool call upstream, returning the result untouched. The captured surface is read-only public YouTube data: there is no upload, comment-posting, messaging, or payment tool in it.
Tools
hasdata_youtube_search_getYoutubeSearchResults— search YouTube. Required:q. Optional filters includegl,hl,deviceType,sp,sortBy,date,videoType,length,filters__, andpaginationToken. Returns video, channel and Shorts results, shelves, ads, and the total-results count.hasdata_youtube_video_getYoutubeVideo— fetch one video by its 11-character ID. Required:v. Optional:gl,hl,deviceType. Returns title, views and likes, duration, channel, description, caption tracks, music matches, and related rails.hasdata_youtube_channel_getYoutubeChannel— fetch one channel by ID (UC...) or handle (@name). Required:channelId. Optional:tab,gl,hl,deviceType,paginationToken. Returns channel identity, subscriber count, and the requested tab's items.hasdata_youtube_transcript_getYoutubeTranscript— fetch a video's timed transcript. Required:v. Optional:languageCode,type(asrfor the auto-generated track). Returns transcript segments plus every available track on the video.
Configuration
HASDATA_YOUTUBE_MCP_URL(optional) — override the upstream endpoint. Defaults tohttps://mcp.hasdata.com/mcp?apis=youtube. (The override hook is this rebuild's own labelled reconstruction.)HASDATA_API_KEY(optional) — when set, every upstream request carries anx-api-key: <key>header, for the caller's own HasData API key. When it is not set, no key header is sent. (The header name and the env name are pinned by the original's registry record; forwarding the key from this env var is a labelled reconstruction — the original surface was captured keyless.)
Forwarding mechanics
On the first tool call the client opens a streamable
HTTP session with the upstream: a JSON-RPC
initialize request (protocolVersion 2025-03-26,
clientInfo name tubedata), then a
notifications/initialized notification, then the
tools/call request carrying the caller's arguments
unchanged. When the upstream answers initialize
with an Mcp-Session-Id header, that value rides on
every later request of the session, which is reused
for the life of the process. Replies may arrive as
plain JSON or as server-sent events; both are read.
Successful upstream results pass through verbatim,
including any isError flag the upstream sets.
Failures — a JSON-RPC error, a non-2xx status, an
unreadable response, or a request that cannot be
completed — come back as an isError result whose
text starts with tubedata error: (this rendering
is this rebuild's own labelled reconstruction).
CLI
Each tool is also a subcommand taking one JSON argument string:
npx @reneturcios/tubedata hasdata_youtube_search_getYoutubeSearchResults '{"q":"lofi beats"}'
npx @reneturcios/tubedata hasdata_youtube_video_getYoutubeVideo '{"v":"dQw4w9WgXcQ"}'
npx @reneturcios/tubedata hasdata_youtube_channel_getYoutubeChannel '{"channelId":"@PewDiePie"}'
npx @reneturcios/tubedata hasdata_youtube_transcript_getYoutubeTranscript '{"v":"dQw4w9WgXcQ","languageCode":"en"}'
npx @reneturcios/tubedata --version
Exit codes: 0 on success, 1 on an isError
result, 2 on a usage error.
MCP server
npx -y @reneturcios/tubedata mcp
MCP client config:
{
"mcpServers": {
"tubedata": {
"command": "npx",
"args": ["-y", "@reneturcios/tubedata", "mcp"]
}
}
}
Docker
docker run -i ghcr.io/cloudcorprecords/tubedata
docker run --rm ghcr.io/cloudcorprecords/tubedata --version
The container's default command is mcp, so the first
form is a stdio MCP server; any other arguments reach
the CLI normally.
Development
npm install
npm run build
npm test
npm run dev
The test suite runs entirely against a stubbed JSON-RPC upstream — no live network calls.
License
MIT — see LICENSE.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.