Skip to main content
Glama
Kick Channels, Streams, and Clips MCP Server

Kick Channels, Streams, and Clips MCP Server

Get Kick channels, streams, and clips

get_kick_channels_streams
Read-onlyIdempotent

Fetch Kick.com channel details, live streams, past broadcasts, and clips; search channels or browse the live directory filtered by category and language.

Instructions

Read public Kick.com data. For each channel name or link: followers, verified mark, bio, social links, recent categories, and live status, with optional past broadcasts and clips. Also searches channels by word and reads the live directory, most viewers first, filtered by category and language.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_kick_channels_streams"
  }
}

Input Schema

NameRequiredDescriptionDefault
searchNoOptional. Words to search Kick channels with, such as poker or valorant. Each word returns its top channels, and each found channel gets a channel row.
channelsNoKick channel names (xqc or @xqc) or links (https://kick.com/xqc). Each channel returns one row with followers, verified mark, bio, social links, recent categories, and live status.
live_nowNoyes to return streams live now, most viewers first, one row per stream. Default no.
clips_sortNoview (default): most viewed first. date: newest first, in Kick's order by clip ID, where clips made within the same minute can appear slightly out of time order.
clips_periodNoWhich clips: day, week, month, or all (default).
include_clipsNoyes to add one row per clip of each channel. Default no.
live_categoryNoOptional, with live_now. A Kick category as it appears in its kick.com link: a main category (games, irl, music, gambling, creative, alternative) or a subcategory such as just-chatting, slots, or valorant.
live_languageNoOptional, with live_now. Keep only streams in this language, such as English, Spanish, or en.
include_videosNoyes to add one row per past broadcast (VOD) of each channel, newest first. Default no.
max_charge_usdNoOptional. The run stops before a charge that would pass this amount. Summary rows are always returned.
max_live_streamsNoLive streams to return, with live_now. Default 50, maximum 1000.
max_clips_per_channelNoClips to return per channel. Kick sends 20 a page. Default 20, maximum 1000.
max_videos_per_channelNoPast broadcasts to return per channel. Kick keeps a limited history, often the last 30 days. Default 20, maximum 500.
max_channels_per_searchNoHow many channels to keep from each search word, in Kick's order. Default 5, maximum 20.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, open-world, non-destructive, so safety is covered; the description adds ordering ('most viewers first'), filtering dimensions, and what optional rows appear. The significant gap is cost: the schema's max_charge_usd implies the run incurs charges, yet the description never mentions that calls can cost money or stop early on a budget, which is a material behavioral trait for an open-world scraper.

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?

Three front-loaded sentences: scope first, then per-channel returns, then the search/directory modes. Dense but not wasteful; the only mild inefficiency is repeating the field list twice (once in sentence one, again in the mode sentence).

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?

For a 14-parameter, multi-mode tool with no output schema, the description does the important work of explaining what rows come back and in what order. It is not fully complete: the relationship between include_* flags and the max_* caps is left implicit, and the charge/budget behavior surfaced by max_charge_usd is never explained.

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 description coverage is 100%, so the parameters are already fully documented; the description largely restates them ('filtered by category and language', 'optional past broadcasts and clips'). It adds the useful framing that channels and search are alternative entry points, but no syntax or semantics beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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 concrete verb and resource ('Read public Kick.com data') and then enumerates the exact payload: followers, verified mark, bio, social links, recent categories, live status, optional past broadcasts and clips. It also names the three operating modes (channel lookup, word search, live directory), so an agent knows precisely what the tool does 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 Guidelines4/5

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

The three modes are clearly distinguished ('For each channel name or link', 'Also searches channels by word', 'reads the live directory'), which tells an agent which input path to take. There are no exclusions or prerequisites stated — e.g., that clips/video parameters only matter when the corresponding include_* flag is set — but the mode framing gives solid contextual guidance.

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