welt-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.
Unofficial read-only MCP server for WELT (welt.de) — one of Germany's biggest daily newspapers — via its official RSS feed (www.welt.de/feeds/latest.rss, no key, no login) and article pages, whose full text is read from the JSON-LD articleBody. Top headlines, news by topic (Deutschland, Ausland, Fußball, Kultur, …), keyword search, the latest video items, and full article text. NOTE: WELT+ (premium) articles expose only their teaser — get_article returns paywalled=true with the teaser for those, never fabricated text; short agency flashes can also be teaser-only (teaser_only=true). Built by Mohammad Abbasi (mohammad-abbasi-sh) — https://almanibama.ir · https://mabbasi.ir — Germany MCP factory.
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 |
|---|---|
| welt_headlinesA | Top headlines from WELT (official RSS feed, 30 items), newest first. limit: 1..50 (default 10). Items carry title, link, teaser, author, category, topic, premium flag (WELT+), subtype (news/video/opinion), image URL and publish time. |
| welt_news_by_topicA | Newest WELT news of one topic, in feed order. topic: a feed category such as "Deutschland", "Ausland", "Fußball", "Kultur", "Film", "Debatte" or "Eishockey" (case-insensitive substring match; any category string works). limit: 1..50 (default 10). |
| welt_search_newsA | Search WELT news by keyword (title + teaser) in the RSS feed. query: free text, e.g. "Bundestag" or "Stromsteuer". limit: 1..50 (default 10). Searches the 30-item feed client-side, newest first, de-duplicated by link. |
| welt_latest_videosA | Latest WELT video items from the RSS feed (subtype "video"), newest first. limit: 1..50 (default 10). |
| welt_get_articleA | Full text of one WELT article page (JSON-LD articleBody). url: a www.welt.de article URL (containing /article or /plus), e.g. from welt_headlines. Returns title, author, publish time, the body text and its word count. For WELT+ (premium) articles only the teaser is freely available: paywalled=true and body holds the teaser. Short agency flashes can be teaser-only too (teaser_only=true, paywalled=false) — the teaser is then the whole freely available text. Nothing is ever fabricated. |
| welt_healthA | Check whether the WELT RSS feed 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
welt_get_article and welt_health are clearly distinct, but four tools (headlines, news_by_topic, search_news, latest_videos) all filter the same 30-item RSS feed and could be confused at the edges — e.g. headlines already contains video and category items. The descriptions do clarify the differences (topic filter vs. keyword search vs. subtype filter), so selection is workable but not perfectly crisp.
All names share the welt_ prefix and snake_case, which makes them scannable and cohesive. There is a minor structural deviation between verb-first names (welt_get_article, welt_search_news) and noun-phrase names (welt_headlines, welt_latest_videos, welt_health), but the pattern remains predictable enough.
Six tools is well-scoped for a read-only news source: one detail fetch, four feed views (headline, topic, search, video) and one health probe. Each tool earns its place with no filler or redundant surface.
The read path is fully covered: discover items, filter by topic or keyword, grab full article text, and check feed availability. Gaps are minor but real — search only spans the 30-item feed with no pagination or date-range query, and there is no tool to enumerate valid topic/category names, forcing agents to guess from the description examples.