Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

tiktok_mobile_mv_videos

Fetch a page of TikTok's mobile music-video channel feed by channel index and cursor. Use it to page through MV tab results as structured aweme JSON.

Instructions

MV channel feed: the app's music-video tab, paged. Returns one page of an MV channel feed, the app's music-video ("MV") tab. The upstream is /aweme/v1/mv/aweme/; mv_id is a small numeric CHANNEL index, NOT a video id — measured ids 0-10 each returned a 15-video page of full aweme objects (1.05-1.24 MB), while 100 returned a valid empty page and a real aweme id returned an empty list. The server's page size is 15 and count was measured IGNORED (count=5 and count=10 both returned 15 items), so count is not exposed; page with cursor. The returned cursor is a reusable next-page token (measured page 1 cursor: 18, has_more: 1; cursor=18 returned a fresh page with cursor: 38, has_more: 1). The envelope's top_awemes (pinned entries), original_aweme_id, page_extra and extra/log_pb are kept as measured. Measured 2026-10-22 with the pure-Go (device-free) signer, so it does not need the device-backed signer. A missing or non-numeric mv_id is a 400; an unknown numeric channel is a valid empty page.

Input Schema

NameRequiredDescriptionDefault
mv_idYesMV channel index (small integer; measured 0-10 populated, 100 empty)
cursorNoNext-page token from the previous response (0 = first page)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.16

TDQS

A4.8/5.0
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: page size 15, `count` measured IGNORED, `cursor` is a reusable next-page token with a concrete measured example (18 -> 38, has_more:1), response sizes ~1.05-1.24 MB, envelope fields kept, and it runs on the device-free signer. That is unusually thorough behavioral disclosure.

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 and information-dense, but the opening repeats itself ('MV channel feed: the app's music-video tab, paged. Returns one page of an MV channel feed, the app's music-video ("MV") tab'), and the measurement provenance parenthetical is verbose. Slightly trimmed it would be ideal.

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

Completeness5/5

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

No output schema exists, yet the description names the envelope's `top_awemes`, `original_aweme_id`, `page_extra`, `extra`/`log_pb`, and states the returned page's shape and pagination fields. Error behavior, auth/signer requirements, and pagination are all covered for a 2-param paged tool.

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 100%, so baseline is 3; the description goes beyond it by warning that `mv_id` is a channel index with measured 0-10 populated / 100 empty, and that a real aweme id returns an empty list. It also explains `cursor` reuse empirically. It adds real semantics rather than restating field descriptions.

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 ('Returns one page of an MV channel feed, the app's music-video tab') and disambiguates the key trap: `mv_id` is a small numeric CHANNEL index, not a video id. An agent can tell exactly what this returns and how it differs from a video-detail endpoint without opening the 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?

Explicitly says when to use it (MV tab browsing, paged) and when not to pass a video id; documents that `count` is ignored and deliberately not exposed, instructing to page with `cursor`. It also states failure modes: missing/non-numeric `mv_id` is a 400, unknown numeric channel is a valid empty page.

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

Deploy Server

Other Tools