grade

search_channels

Busca canais públicos (filtros: q, country, category, language, network, quality, playable, nsfw; kind=radio para estações de rádio, tag para tag de rádio; sort=score ordena pela saúde medida por terceiro, sort=votes pelos votos da rádio; online=1 só quem foi visto online nas últimas 48 h).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`q`	No	Texto livre no nome e nos apelidos do canal (busca full-text).
`tag`	No	Tag da estação de rádio (vocabulário livre do Radio Browser, ex. `mpb`, `news`); veja `GET /api/tags`.
`city`	No	Cidade, código do iptv-org.
`kind`	No	`tv` (padrão) é o catálogo de TV; `radio` são as estações do Radio Browser; `all` junta os dois. Sem `kind`, rádio nunca aparece.	tv
`nsfw`	No	`1` inclui conteúdo adulto; exige consentimento 18+ gravado, senão 403.	0
`sort`	No	`score` ordena pela saúde medida por terceiro (IPTV Nexus), melhor primeiro; canal não medido vai para o fim. `votes` ordena pelos votos da comunidade do Radio Browser (rádio). `name` é a ordem alfabética.	name
`guide`	No	`1` traz só canal com grade de programação (EPG).	0
`online`	No	`1` traz só canal visto online pela fonte (IPTV Nexus para TV, Radio Browser para rádio) nas 48 h anteriores à última recarga do catálogo (`health_ext.online`); com o catálogo parado há mais de 48 h o filtro não devolve ninguém.	0
`country`	No	País do canal, ISO 3166-1 alpha-2.
`network`	No	Nome exato da rede/emissora.
`quality`	No	Qualidade exata do stream.
`category`	No	ID de categoria do iptv-org.
`language`	No	Idioma do canal, ISO 639-3.
`playable`	No	`0` inclui canal sem stream utilizável conhecido.	1
`subdivision`	No	Estado/província, código do iptv-org.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed25 schema fields changedSep 6, 2026

addedInput schema / properties / category / description
```
Added value: +"ID de categoria do iptv-org."
```
addedInput schema / properties / city / description
```
Added value: +"Cidade, código do iptv-org."
```

addedInput schema / properties / country / description

Added value: +"País do canal, ISO 3166-1 alpha-2."

addedInput schema / properties / guide / default
```
Added value: +"0"
```

addedInput schema / properties / guide / description

Added value: +"`1` traz só canal com grade de programação (EPG)."

addedInput schema / properties / guide / enum
```
Added value: +[
+  "0",
+  "1"
+]
```
addedInput schema / properties / kind / default
```
Added value: +"tv"
```

addedInput schema / properties / kind / description

Added value: +"`tv` (padrão) é o catálogo de TV; `radio` são as estações do Radio Browser; `all` junta os dois. Sem `kind`, rádio nunca aparece."

addedInput schema / properties / language / description
```
Added value: +"Idioma do canal, ISO 639-3."
```
addedInput schema / properties / network / description
```
Added value: +"Nome exato da rede/emissora."
```
addedInput schema / properties / nsfw / default
```
Added value: +"0"
```

addedInput schema / properties / nsfw / description

Added value: +"`1` inclui conteúdo adulto; exige consentimento 18+ gravado, senão 403."

addedInput schema / properties / nsfw / enum
```
Added value: +[
+  "0",
+  "1"
+]
```
addedInput schema / properties / online / default
```
Added value: +"0"
```

addedInput schema / properties / online / description

Added value: +"`1` traz só canal visto online pela fonte (IPTV Nexus para TV, Radio Browser para rádio) nas 48 h anteriores à última recarga do catálogo (`health_ext.online`); com o catálogo parado há mais de 48 h o filtro não devolve ninguém."

addedInput schema / properties / online / enum
```
Added value: +[
+  "0",
+  "1"
+]
```
addedInput schema / properties / playable / default
```
Added value: +"1"
```

addedInput schema / properties / playable / description

Added value: +"`0` inclui canal sem stream utilizável conhecido."

addedInput schema / properties / playable / enum
```
Added value: +[
+  "0",
+  "1"
+]
```

addedInput schema / properties / q / description

Added value: +"Texto livre no nome e nos apelidos do canal (busca full-text)."

addedInput schema / properties / quality / description
```
Added value: +"Qualidade exata do stream."
```
addedInput schema / properties / sort / default
```
Added value: +"name"
```

addedInput schema / properties / sort / description

Added value: +"`score` ordena pela saúde medida por terceiro (IPTV Nexus), melhor primeiro; canal não medido vai para o fim. `votes` ordena pelos votos da comunidade do Radio Browser (rádio). `name` é a ordem alfabética."

addedInput schema / properties / subdivision / description

Added value: +"Estado/província, código do iptv-org."

addedInput schema / properties / tag / description

Added value: +"Tag da estação de rádio (vocabulário livre do Radio Browser, ex. `mpb`, `news`); veja `GET /api/tags`."

First observedSep 6, 2026

TDQS

A3.8/5.0

Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses behavioral quirks like the 48-hour online window, that radio is hidden without kind=radio, and that sort=score orders by third-party health with unmeasured channels last. Missing response format or pagination details, but covers key behaviors.

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?

One long sentence but front-loaded with the main purpose and then enumerates filters in parentheses. Efficient though dense; it packs a lot of information without unnecessary words.

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

Completeness3/5

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

With 15 parameters, 6 enums, and no output schema, the description covers the most important filters but omits several (city, guide, subdivision, playable) that are only in the schema. It does not mention the return type, pagination, or any response format, which an agent would need for a search operation.

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 baseline is 3. The description summarizes a few key parameters (kind, sort, online) but does not add meaning beyond the schema's own detailed descriptions. It only restates what the schema already explains.

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 ('Busca') and resource ('canais públicos') and lists key filters. It clearly distinguishes from sibling list_* metadata tools and get_channel by being the search entry point.

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 the tool's purpose; it mentions specific use cases like kind=radio and sort=score, but does not explicitly say when to use this over alternatives like get_channel or list_* tools. No exclusions are given.

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

All grade tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

C2.9/5.0

Disambiguation5/5

Each tool addresses a distinct resource/action: favorites vs. history vs. watch recording are clearly separate, and the NSFW consent/pass tools are unambiguous. Even closely related tools like 'get_channel', 'get_channel_guide', and 'legacy_stream' serve different purposes. No two tools appear to do the same thing.

Naming Consistency4/5

Most tools follow a verb_noun pattern (get_, list_, create_, add_, remove_, etc.) with clear conventions. A few exceptions exist like 'billing', 'geo', 'health', and 'me', which are nouns and break the pattern slightly, but the overall style is predictable and readable.

Tool Count2/5

With 47 tools, the server is far beyond the typical well-scoped range (3-15). While the API covers a broad domain (auth, catalog, chat, comments, billing, NSFW), this many tools would be better split into smaller, focused servers. The count feels bloated and could overwhelm an agent.

Completeness4/5

The tool surface is quite comprehensive for a streaming service: it includes auth, user preferences, favorites, history, catalog search, channel details, comments, chat, NSFW consent/passes, billing, and reporting. Minor gaps exist (e.g., no update/delete for categories/groups, no comment editing), but these are not critical dead ends.

Resources

Need Help?