Combien d'outils expose io.github.fmadore/iwac-mcp-server ?

io.github.fmadore/iwac-mcp-server expose 39 outil(s). Le coût de contexte pour les charger tous est d'environ 15956 tokens (coût unique au chargement, pas par appel).

accueil / serveurs / Fichiers & Documents / io.github.fmadore/iwac-mcp-server

io.github.fmadore/iwac-mcp-server

serveur MCP (Model Context Protocol) · iwac-mcp-server 4.1.0

▸ Fichiers & Documents

[ Non encore testé ]

Verdict MCP Hub
Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur.

streamable-httpType / transport

directAccès

~15956 tokensCoût de contexte

39Outils

Est-ce que io.github.fmadore/iwac-mcp-server est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.fmadore/iwac-mcp-server » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 39 outils

explore_corpus≈ 1111 tokens
Selection workbench: items, concordance, coverage, compare (requires comparison), attention, aliases, or paginated manifest/CSL-JSON/BibTeX exports. Exact filters intersect. Coverage measures archive availability. Exports identify this page and dataset snapshot; compare snapshot IDs across pages. Schema discovery: iwac://datasets/{subset}.
Paramètres, retour & exemple (6)
Paramètres
- mode · string · optionnel · items | concordance | coverage | compare | attention | aliases | manifest | csl_json
- limit · integer · optionnel
- offset · integer · optionnel
- subset · string · optionnel · articles | publications | documents | audiovisual | images | index | references
- selection · object · optionnel
- comparison · object · optionnel
Exemple d'appel
```
{"name": "explore_corpus", "arguments": {"mode": "items", "limit": 1, "offset": 1, "subset": "articles", "selection": {}, "comparison": {}}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"mode": "texte", "note": "texte", "rows": [], "view": "records", "limit": 1, "export": {}, "offset": 1, "subset": "texte", "filters": {}, "metrics": {}, "overlap": 1, "has_more": true}}
```
fetch≈ 385 tokens
Retrieve the full text and metadata of one IWAC item by an id returned from `search` (format '<category>:<number>', e.g. 'articles:28576'). Returns {id, title, text, url, metadata}: `text` is the item's OCR / abstract / transcription / description, `url` is the canonical islam.zmo.de link to cite, and `metadata` holds the remaining fields (author, date, country, newspaper, AI sentiment, …). Categories: articles, publications, references, documents, index, audiovisual, images.
Paramètres, retour & exemple (1)
Paramètres
- id · string · requis
  Item id from search, e.g. 'articles:28576' or 'references:11045'
Exemple d'appel
```
{"name": "fetch", "arguments": {"id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "url": "texte", "text": "texte", "title": "texte", "category": "texte", "metadata": {}, "text_source": "texte", "text_truncated": true, "recommended_tool": "texte", "recommended_usage": {}}}
```
get_article≈ 248 tokens
Get one article (by id): full metadata, the AI abstract (description_ai), AI sentiment, and OCR text, in 25k-char parts (follow `next_offset`). Pass a `keyword` to get ~2000-char excerpts around each match instead.
Paramètres, retour & exemple (5)
Paramètres
- offset · integer · optionnel
  Read from this character on: the previous part's next_offset
- keyword · string · optionnel
  Return excerpts around matches instead of the full OCR (accent-insensitive)
- article_id · integer · requis
- max_excerpts · integer · optionnel
  Default 10, max 25
- context_chars · integer · optionnel
  Default 2000, max 5000
Exemple d'appel
```
{"name": "get_article", "arguments": {"article_id": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
get_audiovisual≈ 255 tokens
Get one audiovisual record by id: full description and transcription (where one exists), creator/publishing channel, duration, medium, subjects, places, language, rights, source, and three distinct links: `url` (the IWAC page, the one to cite), `external_url` (where a harvested video plays) and `media_url` (a deposited file). `source_type` says which to expect. A long transcription comes in 25k-char parts (follow `next_offset`); `keyword` returns excerpts instead.
Paramètres, retour & exemple (3)
Paramètres
- offset · integer · optionnel
  Read from this character on: the previous part's next_offset
- keyword · string · optionnel
- audiovisual_id · integer · requis
Exemple d'appel
```
{"name": "get_audiovisual", "arguments": {"audiovisual_id": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```

get_collection_stats≈ 416 tokens

Overall statistics for every IWAC subset, including `fulltext_coverage` — how many items in each subset actually carry searchable full text in this dataset. Read that before treating any keyword count as a full-text census.

Paramètres, retour & exemple (0)

Exemple d'appel

{"name": "get_collection_stats", "arguments": {}}

Exemple de retour

{"content": [{"type": "text", "text": "…"}], "structuredContent": {"view": "texte", "date_range": {}, "dataset_url": "texte", "fulltext_note": "texte", "subset_counts": {}, "total_records": 1, "failed_subsets": [], "collection_name": "texte", "newspaper_count": 1, "fulltext_coverage": {}, "articles_by_country": {}}}

get_cooccurrence≈ 635 tokens
Count pairs of metadata values co-tagged on the same items. Matrix/network views show descriptive associations, not causal links. Filters apply before pair counting; top_n caps the vocabulary.
Paramètres, retour & exemple (14)
Paramètres
- exact · object · optionnel
  AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.
- field · string · optionnel
  subject (default) | spatial | author | language
- top_n · integer · optionnel
  Values on each axis (default 15, max 30)
- subset · string · optionnel
  articles (default) | publications | references
- country · string · optionnel
  Exact country name (accents optional)
- date_to · string · optionnel
- keyword · string · optionnel
- subject · string · optionnel
  Exact tag
- date_from · string · optionnel
  Inclusive date bounds: YYYY[-MM[-DD]]
- newspaper · string · optionnel
  Newspaper/periodical substring
- hijri_year · integer · optionnel
- hijri_month · string · optionnel
- keyword_mode · string · optionnel · literal | all_terms
- keyword_aliases · array · optionnel
Exemple d'appel
```
{"name": "get_cooccurrence", "arguments": {"exact": {}, "field": "texte", "top_n": 1, "subset": "texte", "country": "texte", "date_to": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "view": "texte", "field": "texte", "matrix": [], "subset": "texte", "values": [], "filters": {}, "top_pairs": [], "total_matches": 1}}
```

get_country_comparison≈ 211 tokens

Compare article counts, newspaper counts, date ranges, and gpt-5-6-luna polarity across countries.

Paramètres, retour & exemple (0)

Exemple d'appel

{"name": "get_country_comparison", "arguments": {}}

Exemple de retour

{"content": [{"type": "text", "text": "…"}], "structuredContent": {"view": "texte", "countries": [], "polarity_model": "texte", "total_countries": 1}}

get_document≈ 251 tokens
Get one archival document (by id): full metadata, AI description, and OCR text, in 25k-char parts (follow `next_offset`). Pass a `keyword` to get ~2000-char excerpts around each match instead, useful for long documents.
Paramètres, retour & exemple (5)
Paramètres
- offset · integer · optionnel
  Read from this character on: the previous part's next_offset
- keyword · string · optionnel
  Return excerpts around matches instead of the full OCR (accent-insensitive)
- document_id · integer · requis
- max_excerpts · integer · optionnel
  Default 10, max 25
- context_chars · integer · optionnel
  Default 2000, max 5000
Exemple d'appel
```
{"name": "get_document", "arguments": {"document_id": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
get_field_distribution≈ 704 tokens
Rank exact metadata values, splitting pipe-separated tags. Reports missing metadata and optional coverage over time. Choose spatial for mentioned places, country for stored country tags, or subject/author/language.
Paramètres, retour & exemple (15)
Paramètres
- exact · object · optionnel
  AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.
- field · string · requis
  subject | spatial | author | language | newspaper | country
- top_n · integer · optionnel
  Values returned (default 25, max 100)
- subset · string · optionnel
  articles (default) | publications | references
- country · string · optionnel
  Exact country name (accents optional)
- date_to · string · optionnel
- keyword · string · optionnel
- subject · string · optionnel
  Exact tag
- date_from · string · optionnel
  Inclusive date bounds: YYYY[-MM[-DD]]
- newspaper · string · optionnel
  Newspaper/periodical substring
- over_time · boolean · optionnel
  Also return the per-year share of items carrying a value
- hijri_year · integer · optionnel
- hijri_month · string · optionnel
- keyword_mode · string · optionnel · literal | all_terms
- keyword_aliases · array · optionnel
Exemple d'appel
```
{"name": "get_field_distribution", "arguments": {"field": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "view": "texte", "field": "texte", "subset": "texte", "values": [], "filters": {}, "other_values": 1, "total_matches": 1, "distinct_values": 1, "coverage_by_year": {}, "items_with_value": 1}}
```
get_image≈ 148 tokens
Get one photograph by id: title, photographer, capture date, place and coordinates, subjects, rights, the IIIF manifest, and the full-resolution `image_url`. The server returns URLs, not image bytes.
Paramètres, retour & exemple (1)
Paramètres
- image_id · integer · requis
Exemple d'appel
```
{"name": "get_image", "arguments": {"image_id": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
get_index_entry≈ 127 tokens
Get full details of an index entry by id (raw dataset columns, French names — Titre, Prénom, Coordonnées…).
Paramètres, retour & exemple (1)
Paramètres
- entry_id · integer · requis
Exemple d'appel
```
{"name": "get_index_entry", "arguments": {"entry_id": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
get_lexical_metrics≈ 618 tokens
Text length, lexical richness and readability by country/newspaper/year. Metrics are precomputed; readability is French-specific and excludes other languages. Missing values are disclosed. Compare distributions as descriptive evidence.
Paramètres, retour & exemple (13)
Paramètres
- exact · object · optionnel
  AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.
- top_n · integer · optionnel
  Groups returned when grouping by newspaper (default 20, max 60)
- country · string · optionnel
  Exact country name (accents optional)
- date_to · string · optionnel
- keyword · string · optionnel
- subject · string · optionnel
  Exact tag
- group_by · string · optionnel
  year (default) | newspaper | country
- date_from · string · optionnel
  Inclusive date bounds: YYYY[-MM[-DD]]
- newspaper · string · optionnel
  Newspaper/periodical substring
- hijri_year · integer · optionnel
- hijri_month · string · optionnel
- keyword_mode · string · optionnel · literal | all_terms
- keyword_aliases · array · optionnel
Exemple d'appel
```
{"name": "get_lexical_metrics", "arguments": {"exact": {}, "top_n": 1, "country": "texte", "date_to": "texte", "keyword": "texte", "subject": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "view": "texte", "groups": [], "filters": {}, "metrics": {}, "group_by": "texte", "total_matches": 1, "readability_excluded": 1}}
```
get_newspaper_stats≈ 248 tokens
Per-newspaper article counts and date ranges.
Paramètres, retour & exemple (1)
Paramètres
- country · string · optionnel
  Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Togo (accents optional)
Exemple d'appel
```
{"name": "get_newspaper_stats", "arguments": {"country": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"view": "texte", "newspapers": [], "country_filter": "texte", "total_articles": 1, "total_newspapers": 1}}
```
get_place_distribution≈ 664 tokens
Place tags joined to authority coordinates. Separates publication countries from mentioned places; missing geocodes are counted explicitly.
Paramètres, retour & exemple (13)
Paramètres
- exact · object · optionnel
  AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.
- top_n · integer · optionnel
  Geocoded places returned (default 60, max 200)
- subset · string · optionnel
  articles (default) | publications | references
- country · string · optionnel
  Exact country name (accents optional)
- date_to · string · optionnel
- keyword · string · optionnel
- subject · string · optionnel
  Exact tag
- date_from · string · optionnel
  Inclusive date bounds: YYYY[-MM[-DD]]
- newspaper · string · optionnel
  Newspaper/periodical substring
- hijri_year · integer · optionnel
- hijri_month · string · optionnel
- keyword_mode · string · optionnel · literal | all_terms
- keyword_aliases · array · optionnel
Exemple d'appel
```
{"name": "get_place_distribution", "arguments": {"exact": {}, "top_n": 1, "subset": "texte", "country": "texte", "date_to": "texte", "keyword": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "view": "texte", "places": [], "subset": "texte", "filters": {}, "ungeocoded": [], "total_matches": 1, "geocode_coverage": {}, "items_by_country": {}, "items_with_place": 1, "ungeocoded_mentions": 1}}
```
get_publication_fulltext≈ 226 tokens
Full OCR text of a publication in 25k-char parts (follow `next_offset`), or ~2000-char excerpts around keyword matches (accent-insensitive; capped: see match_count vs excerpts_returned).
Paramètres, retour & exemple (5)
Paramètres
- offset · integer · optionnel
  Read from this character on: the previous part's next_offset
- keyword · string · optionnel
- max_excerpts · integer · optionnel
  Default 10, max 25
- context_chars · integer · optionnel
  Default 2000, max 5000
- publication_id · integer · requis
Exemple d'appel
```
{"name": "get_publication_fulltext", "arguments": {"publication_id": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
get_reference≈ 150 tokens
Full bibliographic record for one academic reference (by id), including the complete abstract (present for ~51% of references), subjects, DOI/URL, and host-work details (book, volume, issue, pages).
Paramètres, retour & exemple (1)
Paramètres
- reference_id · integer · requis
Exemple d'appel
```
{"name": "get_reference", "arguments": {"reference_id": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
get_semantic_map≈ 747 tokens
Stable-hash sample of matching stored embeddings, projected with PCA. Reports eligible, invalid, missing and capped counts, seed and explained variance. Group counts describe the sample. Coordinates are chart-only; this is not the published UMAP landscape. Needs no API key.
Paramètres, retour & exemple (14)
Paramètres
- exact · object · optionnel
  AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.
- limit · integer · optionnel
  Items projected (default 300, max 2000)
- subset · string · optionnel
  articles (default) | documents | publications | references
- country · string · optionnel
  Exact country name (accents optional)
- date_to · string · optionnel
- keyword · string · optionnel
- subject · string · optionnel
  Exact tag
- color_by · string · optionnel
  country | newspaper | subject | lda_topic_label | polarity (gpt-5-6-luna's label)
- date_from · string · optionnel
  Inclusive date bounds: YYYY[-MM[-DD]]
- newspaper · string · optionnel
  Newspaper/periodical substring
- hijri_year · integer · optionnel
- hijri_month · string · optionnel
- keyword_mode · string · optionnel · literal | all_terms
- keyword_aliases · array · optionnel
Exemple d'appel
```
{"name": "get_semantic_map", "arguments": {"exact": {}, "limit": 1, "subset": "texte", "country": "texte", "date_to": "texte", "keyword": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "seed": "texte", "view": "texte", "groups": {}, "points": [], "subset": "texte", "filters": {}, "color_by": "texte", "sampling": "texte", "projected": 1, "limit_warning": "texte", "total_matches": 1}}
```
get_sentiment_distribution≈ 942 tokens
Aggregate AI labels over a shared selection. model:"all" compares independent annotators and their coverage; model:"consensus" reads the stored panel majority. Choose compare_models and agreement_field for pairwise Cohen's kappa and quadratic weighted kappa, with explicit denominators. Labels are interpretations, not ground truth; subjectivity is weak evidence and its caveat must accompany findings.
Paramètres, retour & exemple (14)
Paramètres
- exact · object · optionnel
  AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.
- model · string · optionnel
  gpt-5-6-luna | mistral-small-2603 | deepseek-v4-flash-0731 | gemma-4-31b-it | qwen3-8-27b | all | consensus; default gpt-5-6-luna. Vendor aliases accepted; retired models rejected.
- country · string · optionnel
  Exact country name (accents optional)
- date_to · string · optionnel
- keyword · string · optionnel
- subject · string · optionnel
  Exact tag
- date_from · string · optionnel
  Inclusive date bounds: YYYY[-MM[-DD]]
- newspaper · string · optionnel
  Newspaper/periodical substring
- hijri_year · integer · optionnel
- hijri_month · string · optionnel
- keyword_mode · string · optionnel · literal | all_terms
- compare_models · array · optionnel
  Pair of model IDs or aliases; requires model:"all"
- agreement_field · string · optionnel · polarity | centrality | subjectivity
- keyword_aliases · array · optionnel
Exemple d'appel
```
{"name": "get_sentiment_distribution", "arguments": {"exact": {}, "model": "texte", "country": "texte", "date_to": "texte", "keyword": "texte", "subject": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "view": "texte", "model": "texte", "models": [], "filters": {}, "by_model": {}, "coverage": {}, "disputed": {}, "agreement": {}, "consensus": {}, "model_caveat": "texte", "subjectivity": {}}}
```
get_similar_items≈ 429 tokens
Nearest stored embeddings by cosine similarity. Articles and documents lead with the dataset's published top 10. Scores run high (unrelated ~0.7) and rank reading candidates; >= 0.97 suggests a near-duplicate, but no threshold proves a reprint. Returns source IDs and dates. Corpus-wide candidate generation belongs offline.
Paramètres, retour & exemple (4)
Paramètres
- id · string · requis
  Item id — either a bare o:id ('3064') or the namespaced form search returns ('articles:3064')
- limit · integer · optionnel
  Neighbours returned (default 12, max 50)
- subset · string · optionnel
  articles (default) | documents | publications | references
- min_score · number · optionnel
  Minimum cosine similarity (-1 to 1)
Exemple d'appel
```
{"name": "get_similar_items", "arguments": {"id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "view": "texte", "source": {}, "subset": "texte", "neighbours": [], "stored_count": 1, "neighbours_source": "texte"}}
```
get_temporal_distribution≈ 959 tokens
Counts by Gregorian or Hijri year/month, or pooled lunar month. Group by country/newspaper. Partial dates and missing lunar dates are disclosed. normalize_by returns numerator counts and per-bucket denominators in the same country/outlet/date scope, removing thematic filters. Shares describe IWAC holdings.
Paramètres, retour & exemple (16)
Paramètres
- exact · object · optionnel
  AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.
- subset · string · optionnel
  articles (default) | publications | references | documents | audiovisual | images
- country · string · optionnel
  Exact country name (accents optional)
- date_to · string · optionnel
- keyword · string · optionnel
- subject · string · optionnel
  Exact tag
- calendar · string · optionnel
  gregorian (default) | hijri — bucket by the Islamic (Umm al-Qura) calendar
- group_by · string · optionnel
  country | newspaper — one distribution per group value
- date_from · string · optionnel
  Inclusive date bounds: YYYY[-MM[-DD]]
- newspaper · string · optionnel
  Newspaper/periodical substring
- hijri_year · integer · optionnel
- granularity · string · optionnel
  year (default) | month | lunar_month (all years collapsed into 12 lunar months; needs calendar=hijri)
- hijri_month · string · optionnel
- keyword_mode · string · optionnel · literal | all_terms
- normalize_by · string · optionnel · scope | searchable
  Share per bucket in the same country/outlet/date scope; searchable restricts both counts to full text. Thematic filters are removed from the denominator.
- keyword_aliases · array · optionnel
Exemple d'appel
```
{"name": "get_temporal_distribution", "arguments": {"exact": {}, "subset": "texte", "country": "texte", "date_to": "texte", "keyword": "texte", "subject": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "view": "texte", "subset": "texte", "filters": {}, "calendar": "texte", "group_by": "texte", "dated_count": 1, "granularity": "texte", "denominators": {}, "distribution": {}, "month_labels": {}, "normalize_by": "texte"}}
```
get_topic_distribution≈ 738 tokens
Counts of offline LDA topic assignments, optionally over time. Topic labels are interpretive model outputs; exact topic_id filters select assignments rather than keyword matches. Reports unclassified coverage.
Paramètres, retour & exemple (15)
Paramètres
- exact · object · optionnel
  AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.
- top_n · integer · optionnel
  Topics given their own band in over_time (default 8, max 15)
- subset · string · optionnel
  articles (default) | references
- country · string · optionnel
  Exact country name (accents optional)
- date_to · string · optionnel
- keyword · string · optionnel
- subject · string · optionnel
  Exact tag
- min_prob · number · optionnel
  0-1; keep only assignments at or above this probability
- date_from · string · optionnel
  Inclusive date bounds: YYYY[-MM[-DD]]
- newspaper · string · optionnel
  Newspaper/periodical substring
- over_time · boolean · optionnel
  Also return per-year counts for the leading topics
- hijri_year · integer · optionnel
- hijri_month · string · optionnel
- keyword_mode · string · optionnel · literal | all_terms
- keyword_aliases · array · optionnel
Exemple d'appel
```
{"name": "get_topic_distribution", "arguments": {"exact": {}, "top_n": 1, "subset": "texte", "country": "texte", "date_to": "texte", "keyword": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "span": [], "view": "texte", "subset": "texte", "topics": [], "filters": {}, "periods": [], "classified": 1, "total_matches": 1, "trend_by_topic": {}, "series_by_topic": {}}}
```
list_audiovisual≈ 284 tokens
List audiovisual materials, newest first (francophone web video from Burkina Faso, Togo and Benin; deposited Nigerian Hausa/Arabic recordings). Filter by country, publishing channel or `source_type`.
Paramètres, retour & exemple (5)
Paramètres
- limit · integer · optionnel
  Default 20, max 50
- offset · integer · optionnel
- country · string · optionnel
  Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Nigeria | Togo (accents optional). Burkina Faso, Togo, Benin and Nigeria only — no Niger or Ivorian items
- publisher · string · optionnel
  Substring on the publishing channel/broadcaster, e.g. RTB | AEEM | CERFI
- source_type · string · optionnel
  youtube (harvested web video, the large majority) | deposited (recordings with a file, 47)
Exemple d'appel
```
{"name": "list_audiovisual", "arguments": {"limit": 1, "offset": 1, "country": "texte", "publisher": "texte", "source_type": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
list_locations≈ 279 tokens
List lieux from the IWAC index, sorted by frequency (most-referenced first). The optional 'country' filter selects entries that APPEAR IN records from that country (mentioned-in, not located-in), ranked by collection-wide 'frequency' — so foreign and cross-border entries can appear. Nigeria returns none here (index frequency is computed from articles + publications + references, which have no Nigerian items — Nigeria is audiovisual only).
Paramètres, retour & exemple (3)
Paramètres
- limit · integer · optionnel
  Default 50, max 200
- offset · integer · optionnel
- country · string · optionnel
  Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Nigeria | Togo (accents optional). Selects lieux MENTIONED IN records from that country, not entities located there
Exemple d'appel
```
{"name": "list_locations", "arguments": {"limit": 1, "offset": 1, "country": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
list_periodicals≈ 268 tokens
List the Islamic periodical/series titles in the publications subset, with issue counts and year ranges. Use the returned newspaper value as the `newspaper` filter on search_publications.
Paramètres, retour & exemple (1)
Paramètres
- country · string · optionnel
  Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Togo (accents optional)
Exemple d'appel
```
{"name": "list_periodicals", "arguments": {"country": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"view": "texte", "periodicals": [], "country_filter": "texte", "total_periodicals": 1}}
```
list_persons≈ 283 tokens
List personnes from the IWAC index, sorted by frequency (most-referenced first). The optional 'country' filter selects entries that APPEAR IN records from that country (mentioned-in, not located-in), ranked by collection-wide 'frequency' — so foreign and cross-border entries can appear. Nigeria returns none here (index frequency is computed from articles + publications + references, which have no Nigerian items — Nigeria is audiovisual only).
Paramètres, retour & exemple (3)
Paramètres
- limit · integer · optionnel
  Default 50, max 200
- offset · integer · optionnel
- country · string · optionnel
  Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Nigeria | Togo (accents optional). Selects personnes MENTIONED IN records from that country, not entities located there
Exemple d'appel
```
{"name": "list_persons", "arguments": {"limit": 1, "offset": 1, "country": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
list_subjects≈ 130 tokens
List sujets from the IWAC index, sorted by frequency (most-referenced first).
Paramètres, retour & exemple (2)
Paramètres
- limit · integer · optionnel
  Default 50, max 200
- offset · integer · optionnel
Exemple d'appel
```
{"name": "list_subjects", "arguments": {"limit": 1, "offset": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
search≈ 679 tokens
Search the Islam West Africa Collection across newspaper articles, Islamic publications, archival documents, academic references, audiovisual recordings, photographs, and the authority index (persons/places/organisations/events/subjects). Pass ONE concept or name — e.g. 'Tijaniyya', 'laïcité', 'Sheikh Gumi', 'pèlerinage'. Matching is accent- and case-insensitive; a multi-word query requires every word to appear somewhere in the item, so prefer a single concept per call. Write query strings and concept keywords in French for press/publication/document/index discovery even when the user's report language is not French. Academic references are multilingual, so try French and English title/abstract terms when relevant; metadata/filter labels remain French. Use the French transliteration of Islamic terms (Tabaski not 'Eid al-Adha', charia not 'sharia', Maouloud not 'Mawlid'). Returns {results:[{id,title,url,category}], ranking}; each result's `category` names its subset and the `ranking` field documents the ordering. Pass an id to `fetch` to read the full text. For filtered queries (by country, date, or newspaper) use the search_* tools instead.
Paramètres, retour & exemple (2)
Paramètres
- limit · integer · optionnel
  Max results across all categories. Default 20, max 50.
- query · string · requis
  One concept, name, or short phrase; use French concept terms for primary sources, and French/English terms for references
Exemple d'appel
```
{"name": "search", "arguments": {"query": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "limit": 1, "ranking": "texte", "results": [], "deep_scan": true, "limit_warning": "texte", "requested_limit": 1, "search_coverage": {}, "coverage_warning": "texte", "unavailable_categories": []}}
```
search_articles≈ 587 tokens
Search IWAC newspaper articles by keyword (title + OCR + AI abstracts, French and English), country, newspaper, subject, and date range. Use French concept keywords regardless of the user's report language. Matching is accent- and case-insensitive.
Paramètres, retour & exemple (14)
Paramètres
- exact · object · optionnel
  AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.
- limit · integer · optionnel
  Default 20, max 100 (10 and 25 with with_description)
- offset · integer · optionnel
- country · string · optionnel
  Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Togo (accents optional)
- date_to · string · optionnel
  YYYY-MM-DD (or YYYY)
- keyword · string · optionnel
  Concept keyword; substring match on title, OCR text, and the French and English AI abstracts. Prefer French for the OCR; an English term still matches via the English abstract
- subject · string · optionnel
- date_from · string · optionnel
  YYYY-MM-DD (or YYYY)
- newspaper · string · optionnel
- hijri_year · integer · optionnel
  Islamic (Umm al-Qura) year, e.g. 1445
- hijri_month · string · optionnel
  Islamic lunar month: 1-12, or a name (Ramadan, Chaabane, Chawwal, Dhu al-Hijja). Pulls the articles behind an observance peak — matches only items with a full YYYY-MM-DD date.
- keyword_mode · string · optionnel · literal | all_terms
- keyword_aliases · array · optionnel
- with_description · boolean · optionnel
  Include each article's ~500-char AI abstract (description_ai) for triage without get_article. Adds ~125 tokens/row, so `limit` defaults to 10 and caps at 25 while this is on.
Exemple d'appel
```
{"name": "search_articles", "arguments": {"exact": {}, "limit": 1, "offset": 1, "country": "texte", "date_to": "texte", "keyword": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
search_audiovisual≈ 491 tokens
Search audiovisual materials by keyword and metadata: francophone web video from Burkina Faso, Togo and Benin (TV reports, association and campus recordings), plus deposited Nigerian Hausa/Arabic recordings. Keyword matches title, creator, publisher, subject, spatial, language, source, the item's own description (the richest text most of these items have) and its transcription where one exists. Each row says which population it is from (`source_type`) and carries either `external_url` (a video to watch) or `media_url` (a file), never both.
Paramètres, retour & exemple (9)
Paramètres
- limit · integer · optionnel
  Default 20, max 50
- medium · string · optionnel
  Exact carrier medium: Vidéo sur le web | DVD | CD (validated, accents optional)
- offset · integer · optionnel
- country · string · optionnel
  Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Nigeria | Togo (accents optional). Burkina Faso, Togo, Benin and Nigeria only — no Niger or Ivorian items
- keyword · string · optionnel
  Substring match across audiovisual title/metadata fields
- subject · string · optionnel
  Exact subject tag — only ~27 rows carry one, so prefer publisher/keyword
- language · string · optionnel
  Exact language value, e.g. Français | Haoussa | Arabe | Anglais | Mooré
- publisher · string · optionnel
  Substring on the publishing channel/broadcaster, e.g. RTB | AEEM | CERFI
- source_type · string · optionnel
  youtube (harvested web video, the large majority) | deposited (recordings with a file, 47)
Exemple d'appel
```
{"name": "search_audiovisual", "arguments": {"limit": 1, "medium": "texte", "offset": 1, "country": "texte", "keyword": "texte", "subject": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
search_by_sentiment≈ 428 tokens
Filter articles by gpt-5-6-luna sentiment labels (accent/case-insensitive exact match). One model's reading, not a consensus — 4 other models scored the same articles and often disagree; get_sentiment_distribution with model:"all" shows by how much. `subjectivity` is much the weakest of the three scales, so treat a set selected on it as a lead to read rather than as a finding.
Paramètres, retour & exemple (8)
Paramètres
- limit · integer · optionnel
  Default 20, max 100
- offset · integer · optionnel
- country · string · optionnel
  Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Togo (accents optional)
- subject · string · optionnel
- disputed · string · optionnel
  polarite | centralite | subjectivite — keep only articles the panel SPLIT on for that field (French field names, as stored). Selects contested readings, not a sentiment value.
- polarity · string · optionnel
  Très positif | Positif | Neutre | Négatif | Très négatif | Non applicable
- centrality · string · optionnel
  Très central | Central | Secondaire | Marginal | Non abordé
- subjectivity · string · optionnel
  Très objectif | Plutôt objectif | Mixte | Plutôt subjectif | Très subjectif — least to most subjective. Unscored where the model answered Non abordé, so this filter also excludes those.
Exemple d'appel
```
{"name": "search_by_sentiment", "arguments": {"limit": 1, "offset": 1, "country": "texte", "subject": "texte", "disputed": "texte", "polarity": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
search_documents≈ 272 tokens
Search the small archival-documents subset (~26 items: Islamic association reports, flyers, project documents — mostly Burkina Faso). Use French concept keywords regardless of the user's report language. Most have OCR text and an AI description. Call with no arguments to list all.
Paramètres, retour & exemple (4)
Paramètres
- limit · integer · optionnel
  Default 15, max 50
- offset · integer · optionnel
- country · string · optionnel
  Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Nigeria | Togo (accents optional). Corpus is mostly Burkina Faso/Togo/Benin
- keyword · string · optionnel
  Concept keyword; substring match on title, OCR, the French and English AI descriptions, and subject (accent-insensitive)
Exemple d'appel
```
{"name": "search_documents", "arguments": {"limit": 1, "offset": 1, "country": "texte", "keyword": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
search_images≈ 401 tokens
Search the IWAC photographs (30 items: mosques, radio stations, schools, signage and street scenes documented during fieldwork). Keyword matches title, creator, subject, place and the rare caption. Each result carries `image_url` (the full-resolution file), `coordinates` ('lat, lng' where known) and the canonical IWAC page. Call with no arguments to list all. Captions are almost never present, so prefer subject/place filters over keywords, or semantic_search_images when it is enabled.
Paramètres, retour & exemple (9)
Paramètres
- limit · integer · optionnel
  Default 20, max 50
- offset · integer · optionnel
- country · string · optionnel
  Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Nigeria | Togo (accents optional)
- creator · string · optionnel
  Photographer name (substring match)
- date_to · string · optionnel
  YYYY-MM-DD (or YYYY)
- keyword · string · optionnel
  French concept keyword; substring match on title, creator, subject, place and caption
- spatial · string · optionnel
  Exact place name, e.g. Ouagadougou (pipe-aware)
- subject · string · optionnel
  Exact subject tag (pipe-aware)
- date_from · string · optionnel
  YYYY-MM-DD (or YYYY)
Exemple d'appel
```
{"name": "search_images", "arguments": {"limit": 1, "offset": 1, "country": "texte", "creator": "texte", "date_to": "texte", "keyword": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
search_index≈ 228 tokens
Search the IWAC authority index (persons, places, organisations, events, subjects) by name. Accent/case-insensitive.
Paramètres, retour & exemple (4)
Paramètres
- limit · integer · optionnel
  Default 20, max 100
- offset · integer · optionnel
- keyword · string · requis
  Search term matched against the entry title
- index_type · string · optionnel
  Exact type (accents optional), validated against: Personnes | Lieux | Organisations | Événements | Sujets | Notices d'autorité. An unrecognised value returns an error listing the valid types.
Exemple d'appel
```
{"name": "search_index", "arguments": {"keyword": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
search_publications≈ 564 tokens
Search Islamic publications (periodical issues, books). `keyword` matches title, subject, table of contents, and full OCR text (TOC hits come back as matching_toc_entries); use French concept keywords regardless of the user's report language. Filter by newspaper/series, subject, country and year. Use list_periodicals to discover series titles, and get_publication_fulltext for keyword excerpts from a single issue.
Paramètres, retour & exemple (13)
Paramètres
- exact · object · optionnel
  AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.
- limit · integer · optionnel
  Default 20, max 100
- offset · integer · optionnel
- country · string · optionnel
  Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Togo (accents optional)
- date_to · string · optionnel
  Latest year, YYYY
- keyword · string · optionnel
  French concept keyword; substring match on title + subject + table of contents + OCR (accent-insensitive)
- subject · string · optionnel
  Subject tag (~87% of issues are tagged)
- date_from · string · optionnel
  Earliest year, YYYY
- newspaper · string · optionnel
  Periodical/series title (see list_periodicals)
- hijri_year · integer · optionnel
  Islamic (Umm al-Qura) year, e.g. 1445
- hijri_month · string · optionnel
  Islamic lunar month: 1-12, or a name (Ramadan, Chaabane, Chawwal, Dhu al-Hijja). Matches only issues with a full YYYY-MM-DD date — ~83% of them.
- keyword_mode · string · optionnel · literal | all_terms
- keyword_aliases · array · optionnel
Exemple d'appel
```
{"name": "search_publications", "arguments": {"exact": {}, "limit": 1, "offset": 1, "country": "texte", "date_to": "texte", "keyword": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
search_references≈ 516 tokens
Search academic references (journal articles, book chapters, theses, books, reports) by keyword and metadata. `keyword` is a single substring match over title + abstract, so search ONE term per call (combined terms like 'pèlerinage Mecque' miss results). References are multilingual: try French and English title/abstract keywords when relevant; metadata/filter values such as `reference_type` and `language` use French labels. Results include a short abstract snippet — use get_reference for the full abstract and bibliographic detail.
Paramètres, retour & exemple (10)
Paramètres
- limit · integer · optionnel
  Default 20, max 100
- author · string · optionnel
- offset · integer · optionnel
- country · string · optionnel
  Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Nigeria | Togo (accents optional)
- date_to · string · optionnel
  Latest year, YYYY
- keyword · string · optionnel
  One French or English concept keyword; substring match on title + abstract (one term per call, accent-insensitive)
- subject · string · optionnel
  Subject tag (sparse: ~27% of references are tagged)
- language · string · optionnel
  e.g. Français | Anglais
- date_from · string · optionnel
  Earliest year, YYYY
- reference_type · string · optionnel
  Substring match. Values: Article de revue | Chapitre de livre | Livre | Mémoire de maitrise | Rapport | Thèse de doctorat | Communication scientifique | Compte rendu de livre | Article d'encyclopédie | Mémoire de licence | Article de blog | Working paper. Use the full label for precision — 'Livre' alone also matches 'Chapitre de livre' and 'Compte rendu de livre'.
Exemple d'appel
```
{"name": "search_references", "arguments": {"limit": 1, "author": "texte", "offset": 1, "country": "texte", "date_to": "texte", "keyword": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
semantic_search_articles≈ 285 tokens
Semantic search over article title + full text, including articles whose OCR is not public. Query in any language. Runs the corpus model, EmbeddingGemma 2, locally with no API key (first use downloads ~350 MB). similarity_score only ranks within one query.
Paramètres, retour & exemple (6)
Paramètres
- limit · integer · optionnel
  Default 10, max 50
- query · string · requis
  Natural-language query, any language
- country · string · optionnel
  Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Togo (accents optional)
- date_to · string · optionnel
  YYYY-MM-DD (or YYYY)
- date_from · string · optionnel
  YYYY-MM-DD (or YYYY)
- newspaper · string · optionnel
Exemple d'appel
```
{"name": "semantic_search_articles", "arguments": {"query": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
semantic_search_images≈ 293 tokens
Find photographs by describing what they SHOW, in any language ('mosquée en construction', 'street signage in Arabic'). This is cross-modal: the ranking runs against a multimodal embedding of the photograph itself, not against a caption, so it works even though only 2 of the 30 images have one. Runs the corpus model, EmbeddingGemma 2, locally with no API key (first use downloads ~350 MB). similarity_score only ranks within one query.
Paramètres, retour & exemple (3)
Paramètres
- limit · integer · optionnel
  Default 10, max 30
- query · string · requis
  Description of the visual content, any language
- country · string · optionnel
  Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Nigeria | Togo (accents optional)
Exemple d'appel
```
{"name": "semantic_search_images", "arguments": {"query": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
semantic_search_publications≈ 278 tokens
Semantic search over publication tables of contents, present for ~40% of issues (none for An-Nasr Vendredi, 130 of 695 Islam Info issues): use search_publications for the rest. Rows show the first 600 characters of each table. Query in any language. Runs the corpus model, EmbeddingGemma 2, locally with no API key (first use downloads ~350 MB). similarity_score only ranks within one query.
Paramètres, retour & exemple (3)
Paramètres
- limit · integer · optionnel
  Default 10, max 50
- query · string · requis
  Natural-language query, any language
- country · string · optionnel
  Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Togo (accents optional)
Exemple d'appel
```
{"name": "semantic_search_publications", "arguments": {"query": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
semantic_search_references≈ 345 tokens
Semantic search over academic references by title + abstract, across languages. Only references with an abstract (about half) are covered; use search_references for the rest. Runs the corpus model, EmbeddingGemma 2, locally with no API key (first use downloads ~350 MB). similarity_score only ranks within one query.
Paramètres, retour & exemple (7)
Paramètres
- limit · integer · optionnel
  Default 10, max 50
- query · string · requis
  Natural-language query, any language
- country · string · optionnel
  Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Nigeria | Togo (accents optional)
- date_to · string · optionnel
  Latest year, YYYY
- language · string · optionnel
  e.g. Français | Anglais
- date_from · string · optionnel
  Earliest year, YYYY
- reference_type · string · optionnel
  French type label, substring (e.g. Thèse de doctorat)
Exemple d'appel
```
{"name": "semantic_search_references", "arguments": {"query": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://islam.zmo.de/mcp/