tabii-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| tabii_search_contentA | Search tabii's catalog by (original Turkish) title. query: a title or part of it, e.g. "gassal", "mevlana", "hobbit". language: "tr" (default), "en", "es", "ar" or "ur" — the returned titles are localized to it. limit 1..10 (default 5). Returns id, slug, localized title, original title, type, year and tabii.com URL per match. Note: matching is against the original Turkish title/slug (the site's own search needs a login) and covers the 1,306 titles in the site's sitemaps — some licensed titles (e.g. The Hobbit) are absent from the sitemaps and cannot be found this way; they are reachable by id via tabii_homepage's featured sections. English titles are shown on the matches but cannot be searched. |
| tabii_get_showA | Full detail of one tabii title. Give show_id (numeric, from tabii_search_content) or slug (e.g. "gassal", "mevlana-celaleddin-i-rumi"). language: "tr" (default), "en", "es", "ar" or "ur". Returns localized title, original title, type, year, genres, age restriction, season count, seasons with episode titles + durations (capped at 60 episodes), cast, directors, writers, description, audio/subtitle languages, badges, trailer count and the tabii.com URL. |
| tabii_homepageA | tabii's current homepage sections: exclusive content, series, movies, documentary and kids — each with its titles (id, slug, localized title, short description). language: "tr" (default), "en", "es", "ar" or "ur". No arguments besides language. |
| tabii_live_channelsA | The 15 live TRT channels on tabii (TRT 1, TRT 2, TRT Belgesel, TRT Haber, TRT Spor, TRT Çocuk, TRT World, ...), each with id, title, slug, watch URL and the public HLS stream URL. language: "tr" (default), "en", "es", "ar" or "ur". No arguments besides language. Note: the streams are the site's public HLS URLs; actual playback may still need a tabii login for some channels. |
| tabii_get_personA | One cast/crew member by numeric tabii person id (from a show's cast/directors/writers lists, e.g. Ahmet Kural is 6774). language: "tr" (default), "en", "es", "ar" or "ur". Returns name, job title and their filmography on tabii (title, original title, type, year, genres per show). |
| tabii_healthA | Check whether tabii.com is reachable right now. Returns status ok (HTTP 200), blocked (HTTP 403/429 — bot wall or rate limit) or error, plus the HTTP status and the probed URL. Two polite requests (homepage + one public show); it does not fetch any listings. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool targets a clearly distinct resource: catalog search, single-title detail, homepage sections, live channels, person filmography, and a health probe. There is no meaningful overlap between title search and homepage browsing, or between show and person lookups.
All names are snake_case with a consistent 'tabii_' prefix, and most follow a verb_noun pattern (search_content, get_show, get_person). A few are noun-only (homepage, live_channels, health), which is a minor deviation but still predictable and readable.
Six tools is a well-scoped surface for a streaming-catalog server: search, detail, browse, live channels, people, and diagnostics. Each tool has a clear role and none feels redundant.
Core workflows (find a title, inspect it, browse homepage, list live channels, look up a person, verify availability) are covered. Gaps remain: search only matches original Turkish titles, some licensed titles are unreachable via search, and there is no genre/type browsing or episode-level retrieval.