YouTube MCP Server

Youtube List Channel Videos

youtube_list_channel_videos

List a channel's recent uploads, newest first — the cheap alternative to searching.

Instructions

List a channel's recent uploads, newest first — the cheap alternative to searching.

Fetches the channel's uploads playlist (via channels.list, cached forever) and walks playlistItems, so this costs one unit from the shared 10,000-unit pool per page of 50 — not the scarce 100/day search.list bucket. Use it whenever the question is "what has this channel posted", instead of youtube_search_videos.

Requires the channel's ID (start from youtube_get_channel if you only have a handle). Each item has the video ID, title, description and when it was added to the playlist; it carries no view counts — get those from youtube_get_video_stats (its own bucket). The walk stops as soon as max_results is reached, so ask for what you need; next_page_token continues from there. For a playlist that is not a channel's uploads, or one you already have the playlist ID for, use youtube_list_playlist_items.

Input Schema

Name	Required	Description	Default
`channel_id`	Yes
`max_results`	No

Output Schema

Name	Required	Description	Default
`items`	No
`channel_id`	Yes
`next_page_token`	No
`uploads_playlist_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.4.0Oct 21, 2026

changedOutput schema / properties / items / items / description

Previous value: -"One `playlistItems.list` item.\n\n`item_id` is the *playlist-item* ID — a different namespace from `video_id`, which\nlives at `snippet.resourceId.videoId` (there is no `contentDetails` part on\nplaylistItems; `video_published_at` arrives implicitly alongside `snippet`)."New value: +"One `playlistItems.list` item.\n\n`item_id` is the *playlist-item* ID — a different namespace from `video_id`, which\nlives at `snippet.resourceId.videoId` (there is no `contentDetails` part on\nplaylistItems; `video_published_at` arrives implicitly alongside `snippet`).\n\n`published_at` is when the video was **added to this playlist** — a playlist keeps its\nown order and its own add-dates, so it says nothing about when the video itself was\npublished to YouTube (`video_published_at` arrives implicitly with `snippet` when YouTube\nincludes it; treat as best-effort)."

First observedv0.1.0Oct 4, 2026

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does so: it discloses the quota economics (1 unit per page of 50 from a shared 10,000 pool vs. the 100/day search bucket), caching behavior ('cached forever'), the pagination/stop-at-max_results semantics, and what the results omit (no view counts) plus where to get them. That is unusually rich operational context for a read tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core one-line purpose and cost framing, then layered detail. It is on the long side and the quota discussion is dense, but nearly every sentence adds actionable information; only the next_page_token remark is wasted due to not matching the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers prerequisites, cost, pagination stops, and result contents, and an output schema exists so return-format detail is not required. The one real gap is the mismatch between the described continuation token and the actual parameter list, which could leave an agent unsure how to page.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate and largely does: it specifies that channel_id is an ID rather than a handle and how to obtain it, and explains that max_results terminates the walk. However, it references `next_page_token` as the continuation mechanism while the schema exposes no such parameter (additionalProperties: false), leaving an ambiguity about how to fetch subsequent pages.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List a channel's recent uploads, newest first') and immediately positions itself against two siblings by name. An agent can distinguish it from youtube_search_videos and youtube_list_playlist_items without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit when-to-use rule ('whenever the question is "what has this channel posted"'), names the alternative to avoid (youtube_search_videos), and names the sibling to use for the adjacent case (non-uploads playlists or known playlist ID). It also states the prerequisite (channel ID, or start from youtube_get_channel with a handle).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server