trthaber-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 |
|---|---|
| trthaber_headlinesA | Top headlines in one TRT Haber category. category: "gundem" (default), "turkiye", "dunya", "turk-dunyasi", "ekonomi", "spor", "savunma", "cocuk", "dunya-disi", "kultur-sanat", "yasam", "saglik", "bilim-teknoloji", "egitim", "cevre", "guncel", "trt-arsiv", "interaktif". limit 1..30 (category pages list 15). Returns headlines (title, article URL, summary when the listing carries one, publish time when shown). |
| trthaber_latestA | Breaking news (son dakika) from TRT Haber, newest first. limit 1..30 (the page lists ~120 articles). Returns articles (title, article URL, summary when present, publish time when shown). |
| trthaber_get_articleA | Full text of one TRT Haber article. article_url: the article's trthaber.com URL (as returned by the headlines/latest/search tools, e.g. "https://www.trthaber.com/haber/bilim-teknoloji/ guney-torid-goktasi-yagmuru-bu-gece-nadir-gorulen-ates-toplari- olusturacak-962288.html"). Returns title, spot, publish date, description, image and the full body text. |
| trthaber_search_newsA | Keyword search over current TRT Haber news: scans the homepage, the breaking-news page and all 18 category listings, matching the keyword in titles and summaries. query: e.g. "ekonomi", "deprem", "COP31". limit 1..30. Note: the site's own /arama search is CSRF-token POST gated, so this searches the current listings instead of a search backend. |
| trthaber_list_categoriesA | The 18 TRT Haber news categories (slug + Turkish display name), for use with trthaber_headlines. No arguments. |
| trthaber_healthA | Check whether trthaber.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. One polite request; 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 distinct retrieval mode: category listing (headlines), breaking-news feed (latest), keyword scan (search_news), full article fetch (get_article), category metadata (list_categories), and reachability (health). The boundaries between headlines, latest, and search_news are explained but still close enough that an agent may hesitate over which to use for a broad keyword-style query.
All six tools share the same `trthaber_` prefix and snake_case verb_noun convention (headlines, latest, list_categories, get_article, search_news, health). The pattern is predictable throughout the set.
Six tools is a tight, well-scoped surface for a single-site news reader, with no redundant or filler tools. Each tool maps to a distinct retrieval need (list, browse, search, fetch, discover categories, health check).
The read lifecycle is complete: discover categories, browse listings, get breaking news, search, and fetch full article text. Minor gaps remain — no date-range or pagination-beyond-limit filtering, and search is limited to current listings rather than the site's full archive.