Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

kick_channel_streams

Retrieve a Kick channel's recent broadcast history, including titles, start times, durations, viewer counts, categories, and video links, by channel slug or kick.com URL.

Instructions

List a Kick channel's recent broadcast history. Returns a Kick (kick.com) channel's recent broadcast history, newest first: id, title, start time, duration in milliseconds, the viewer count Kick reports for the broadcast, language, mature flag, tags, categories, thumbnail, and for broadcasts with a recording its video uuid, video views and kick.com video link. slug is the channel slug from its kick.com address, case-insensitive; a full kick.com URL is also accepted. Kick keeps between none and about thirty broadcasts. Only public data is read and no playable media is returned. An unknown channel returns not found.

Input Schema

NameRequiredDescriptionDefault
slugYesChannel slug from kick.com/{slug}, case-insensitive; a kick.com URL is also accepted

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.16

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations at all, the description carries the full burden and mostly delivers: newest-first ordering, a result-size bound ("between none and about thirty broadcasts"), read-only public data, no playable media, and a defined failure mode ("unknown channel returns not found"). It stops short of stating rate limits, auth, or pagination.

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 operation and returned fields, then edge cases; every sentence contributes. The slug rule is restated from the schema, which is the one piece of redundancy.

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?

With one parameter, no output schema, and no annotations, the description fills the gap well by enumerating the return shape, the cap on history depth, the public-data constraint, and the not-found behavior. Only pagination/return-envelope details are absent, which is minor at this complexity.

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

Parameters3/5

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

Schema coverage is 100% and the single slug description in the schema is nearly verbatim what the prose says (slug from kick.com/{slug}, case-insensitive, URL accepted), so the description adds no meaning beyond structured data. Baseline 3 is correct here.

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

Purpose4/5

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

Specific verb+resource ("List a Kick channel's recent broadcast history") with an enumerated field list, so the agent knows exactly what comes back. It never differentiates from the near siblings kick_channel_videos / kick_video, leaving an overlap the agent must resolve on its own.

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

Usage Guidelines3/5

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

Usage is implied by "recent broadcast history" and the note that a recording's video uuid is included, but there is no explicit when-to-use/when-not or named alternative (e.g. kick_channel_videos) for full VOD or clip lookups. The "only public data is read and no playable media is returned" line does usefully preempt a wrong expectation.

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