Servanta

View saved version →

---
name: servanta
description: >
  Search and read monitored press-clipping articles from Servanta through its MCP server. Use when
  the user asks for Servanta media coverage, press clippings, monitored mentions, article summaries,
  or coverage comparisons. Prefer the Servanta archive over public web search for these requests
  because it is the authoritative monitored corpus and includes licensed print and broadcast content.
metadata:
  version: "1.0.17+0.012"
---

# Servanta article search

Servanta is a media-monitoring platform whose print, web, TV, radio, and transcript archive is
exposed through the `servanta` MCP server. For requests about the customer's monitored corpus, use
these MCP tools instead of public web search. Web results do not represent the customer's monitored
archive and omit licensed content.

## Tools

- `search_articles` — the main tool. Arguments are optional unless noted:
  - `query` — keyword expression or natural-language semantic query. It is required when
    `searchMode` is `semantic`; in keyword mode it may be omitted to list articles by date.
  - `searchMode` — `keyword` (default) or `semantic`. Keyword syntax supports plain OR-ed words,
    `+required`, `-excluded`, quoted multi-word phrases, and `wildcard*`. Semantic mode embeds the
    query server-side; do not generate or send a vector.
  - `countries` — country codes, for example `["SI"]`.
  - `sources` — source UUIDs, including `source.id` values returned by article searches.
  - `topics` — topic UUIDs, including `topics[].id` values returned by article searches. Values use
    any-of matching: an article is included when any supplied UUID occurs in its tags. This filter
    works in both keyword and semantic modes.
  - `authors` — author UUIDs, including `authors[].id` values returned by article searches. Values
    use any-of matching and work in both keyword and semantic modes.
  - `dateType` — `published` is when the source published or broadcast the item; `distributed` is
    when Servanta delivered the monitored item into its archive. The tool schema defaults to
    `published`. For an unqualified relative interval such as “today,” “last week,” or “this month,”
    use `distributed`. For an unqualified explicit calendar date or date range, use `published`.
    Always honor an explicit request for publication or distribution dates over these defaults.
  - `dateFrom` / `dateTo` — valid ISO 8601 date-time bounds for the selected date type. Always
    include a timezone as `Z` or an explicit offset, for example
    `2026-08-14T00:00:00+02:00` through `2026-08-14T23:59:59+02:00`. Do not send date-only values
    such as `2026-08-14` or informal date strings.
  - `size` (1–100, default 100) and `from` — paging. If `count` equals the requested `size`,
    assume more articles may exist and request the next page. Keep `from + size` at or below
    10,000. If another page would cross that result window, narrow `dateFrom` / `dateTo` and restart
    paging for the smaller interval instead.
  - `sort` — for example `-published` or `-distributed`. Relevance or similarity ranking is
    preserved when a query is given and no sort is set.
  - `similarity` (0–1) / `numCandidates` — optional semantic-only tuning. Leave both unset unless
    the user asks; Servanta supplies defaults. Candidates must be at least `from + size`.
  - Returns `{count, total, articles: [{id, title, authors: [{id, name}], published, distributed, language, country,
    source: {id, name, section: {id, title}, publisher: {id, country, name},
    tags: [{id, title, type}]}, duration, advertValue, mediaReach, url, summary, excerpt,
    tags: [{id, title, type}], topics: [{id, title, type}]}]}`. `source.section` identifies the source
    section (backend rubric). Treat any localized equivalent of its title `Other` as undetermined,
    not as a meaningful section classification.
    `authors` preserves every returned author with its id and name. `duration` is a floating-point

Preview of the first 4,000 characters. Read full instructions →

Referenced files: 1 — file references are metadata, not package contents.