mcp server

Islam West Africa Collection (IWAC)

Read-only access to the Islam West Africa Collection via Hugging Face datasets.

Description as published by the maintainer. Source

• version 1.5.1
• active

active — Most recent push to the repository was 2026-08-07.

What this server can do

34 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

fetch(id)

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. Required: id.

get_article(keyword, article_id, max_excerpts, context_chars)

Get one article (by id): full metadata, the AI abstract (description_ai), AI sentiment, and OCR text. Pass a `keyword` to get ~2000-char excerpts around each match instead of the full (capped) OCR. Required: article_id.

get_audiovisual(audiovisual_id)

Get one audiovisual record by id, including creator/publisher, media URL, duration, medium, subjects, places, language, source, and IWAC URL. Required: audiovisual_id.

get_collection_stats

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

get_cooccurrence(field, top_n, subset, country, date_to, keyword, subject, date_from, newspaper)

How often the top values of a multi-valued field appear on the SAME item — a subject/place co-mention matrix. Answers 'what is X discussed alongside' without reading anything: the pair counts are the structure of the tagging. Returns the top values, the full symmetric matrix (diagonal = each value's own count) and the strongest pairs.

get_country_comparison

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

get_document(keyword, document_id, max_excerpts, context_chars)

Get one archival document (by id): full metadata, AI description, and OCR text. Pass a `keyword` to get ~2000-char excerpts around each match instead of the full (capped) OCR — useful for long documents. Required: document_id.

get_field_distribution(field, top_n, subset, country, date_to, keyword, subject, date_from, newspaper, over_time)

Rank the values of one multi-valued field across a filtered set — the direct way to answer 'which places does this coverage name most', 'who signs these articles', 'what subjects dominate'. Pipe-joined fields (subject, spatial, author, language, country) are split, so an article tagged 'Prière|Ramadan' counts once for each. Optional over_time adds the per-year share of items that carry ANY value for the field, which is how you see e.g. bylines appearing as the press professionalises. Required: field.

get_image(image_id)

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. Required: image_id.

get_index_entry(entry_id)

Get full details of an index entry by id (raw dataset columns, French names — Titre, Prénom, Coordonnées…). Required: entry_id.

get_lexical_metrics(top_n, country, date_to, keyword, subject, group_by, date_from, newspaper)

Readability, lexical richness and length of the press text, averaged by year, newspaper or country. `Lisibilite_OCR` is a French readability score (higher = easier); `Richesse_Lexicale_OCR` is MATTR, a moving-average type-token ratio that is ALREADY length-robust — do not normalise it by word count or bin it by length. Readability is computed against a French lexicon, so non-French items are excluded from that metric (and counted in readability_excluded) rather than reported as unreadable; MATTR and word count need no lexicon and cover everything. Only items whose full text ships in this public dataset carry these columns at all.

get_newspaper_stats(country)

Per-newspaper article counts and date ranges.

get_place_distribution(top_n, subset, country, date_to, keyword, subject, date_from, newspaper)

Places named by a filtered set of items, joined to the index's authority records so each carries coordinates where the index has them. Use this rather than get_field_distribution when the question is geographic — where coverage clusters — and the plain ranking when it is not. Only `Lieux` index entries are geocoded (555 of 683); persons, organisations and events carry no coordinates and never will, and any named place with no index entry comes back under `ungeocoded` rather than being dropped.

get_publication_fulltext(keyword, max_excerpts, context_chars, publication_id)

Full OCR text of a publication, optionally returning ~2000-char excerpts around keyword matches (accent-insensitive; capped — see match_count vs excerpts_returned). Required: publication_id.

get_reference(reference_id)

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). Required: reference_id.

get_semantic_map(limit, subset, country, date_to, keyword, subject, color_by, date_from, newspaper)

A 2-D scatter of a filtered set, projected from the stored 768-dimension embeddings by PCA. Shows which items sit near each other in meaning — where a set splits into distinct strands and where it is one cloud. Read `explained_variance` before drawing any conclusion: with 768 dimensions the first two components usually carry a modest share, and a scatter explaining 6% of the variance is a much weaker claim than one explaining 40%. This is PCA, not UMAP: it spreads the broadest axes of variation and flattens fine cluster structure, so it is not comparable to the semantic landscapes on islam.zmo.de. Needs no API key — the vectors are a column in the dataset — but only items whose full text ships are embedded at all. NOTE the payload scales with `limit`: a point cloud is a chart, not something a text-only client can read, so for those the useful part is the explained-variance summary rather than the coordinates. Keep `limit` low unless a chart is going to be drawn.

get_sentiment_distribution(model, country, subject, newspaper)

Aggregate AI polarity, centrality and subjectivity across a filter set. Three models scored the corpus independently — gpt-5-6-luna, mistral-small-2603, deepseek-v4-flash-0731 — so model:"all" returns each one's distribution plus how often they AGREE. Treat disagreement as a fact about the judgement rather than noise: in a set where the three models split on polarity, no single model's number should be quoted alone. All three scales are ordinal French labels; subjectivity is much the weakest and ships a caveat to quote with it. Articles were scored whether or not their full text ships, so these shares are not subject to the OCR coverage limit; compare scored_by_all against total_articles for the residual gap (the ~51 non-francophone articles are unscored by design).

get_similar_items(id, limit, subset, min_score)

The items nearest to a given one in meaning, by cosine similarity over the stored embeddings. Answers 'what else is like this' without a keyword — it finds pieces on the same event or theme that share no vocabulary. A neighbour above ~0.85 is usually the same story reprinted or lightly rewritten, which is how to spot syndication in this corpus; 0.6-0.8 is 'same subject, different piece'. Needs no API key: the item's own vector is a column, so nothing has to be embedded at request time. This is per-item, NOT the corpus-wide near-duplicate sweep — that is an all-pairs job and belongs offline. Required: id.

get_temporal_distribution(subset, country, date_to, keyword, subject, calendar, group_by, date_from, newspaper, granularity)

Counts of matching items per year (or month) — the direct way to chart coverage trends over time instead of paging through search results. Defaults to articles; also works on publications, references, documents, audiovisual, and images. Accepts the same filters as the corresponding search_* tool (keyword = ONE substring over the subset's text fields, country, newspaper/series, subject, date range). Optional group_by=country|newspaper returns one distribution per group. Items dated only to a year keep a bare-year key even at month granularity; undated items are counted in undated_count, never dropped silently. Set calendar=hijri to bucket by the Islamic (Umm al-Qura) calendar instead — with granularity=lunar_month this collapses every year into the twelve lunar months, which is the ONLY way to see observance-driven coverage (Ramadan, Dhu al-Hijja/hajj, Shawwal/Korité): the lunar year drifts ~11 days against the Gregorian, so a Gregorian axis smears each observance across all twelve months. Hijri buckets need a full YYYY-MM-DD, so items dated only to a year or month are reported in imprecise_date_count.

get_topic_distribution(top_n, subset, country, date_to, keyword, subject, min_prob, date_from, newspaper, over_time)

How a filtered set distributes across the precomputed LDA topics, each labelled by its top terms (articles carry 30 topics and are ~99.5% classified; references have their own 33-topic model and only ~46% carry an assignment, so read its `classified` against `total_matches`). Topics are assigned offline over the full text, so they describe what a piece is ABOUT rather than which words it contains — use this instead of keyword counting to map a corpus. Optional over_time returns per-year counts for the leading topics. min_prob keeps only articles where the topic is at least that dominant (mean assignment probability is 0.34, so 0.5 is already a strong filter).

list_audiovisual(limit, offset, country)

List audiovisual materials (Nigerian recordings, incl. Hausa/Arabic content).

list_locations(limit, offset, country)

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).

list_periodicals(country)

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.

list_persons(limit, offset, country)

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).

list_subjects(limit, offset)

List sujets from the IWAC index, sorted by frequency (most-referenced first).

search(limit, query)

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. Required: query.

search_articles(limit, offset, country, date_to, keyword, subject, date_from, newspaper, hijri_year, hijri_month, with_description)

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.

search_audiovisual(limit, medium, offset, country, keyword, subject, language)

Search audiovisual materials by keyword and metadata. Keyword matches title, creator, publisher, subject, spatial, language, source, and AI description where present.

search_by_sentiment(limit, offset, country, subject, polarity, centrality, subjectivity)

Filter articles by gpt-5-6-luna sentiment labels (accent/case-insensitive exact match). One model's reading, not a consensus — two 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.

search_documents(limit, offset, country, keyword)

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.

search_images(limit, offset, country, creator, date_to, keyword, spatial, subject, date_from)

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.

search_index(limit, offset, keyword, index_type)

Search the IWAC authority index (persons, places, organisations, events, subjects) by name. Accent/case-insensitive. Required: keyword.

search_publications(limit, offset, country, date_to, keyword, subject, date_from, newspaper, hijri_year, hijri_month)

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.

search_references(limit, author, offset, country, date_to, keyword, subject, language, date_from, reference_type)

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.

Last successful function declaration observed on 2026-08-13. Source: https://islam.zmo.de/mcp/. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: https://islam.zmo.de/mcp/.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Repository — https://github.com/fmadore/iwac-mcp-server
• Website — https://islam.zmo.de/s/westafrica/
• Remote endpoint (streamable-http) — https://islam.zmo.de/mcp/

Related, by what their authors tagged them

• io.github.caelum29/calibre-mcp — last commit 2026-08-03, shares claude-desktop, huggingface
  Calibre ebook library server: search, read content, curate metadata, semantic search, gated writes.
• TrainTools — last commit 2026-07-22, shares huggingface
  Recommend paper-backed diagnostics for PyTorch and Hugging Face training problems.
• io.github.Embassy-of-the-Free-Mind/source-library — last commit 2026-08-08, shares digital-humanities
  Search 22,000+ rare pre-modern texts with AI English translations, summaries, and 73K+ images.
• Source Library — last commit 2026-08-08, shares digital-humanities
  Search 15K rare pre-modern texts translated to English: philosophy, religion, science, literature.
• Proton Drive CLI MCP — last commit 2026-06-12, shares claude-desktop, mcpb
  Manage Proton Drive from MCP clients through Proton's official CLI without exposing credentials.
• app.reassign/reassign — last commit 2026-07-25, shares mcpb
  Reassign: a circular 24-hour calendar and time-tracking copilot with ADHD-friendly scheduling.
• ContrastAPI — last commit 2026-08-04, shares mcpb
  55 tools, 7 Resources, Sigma rules, email SPF/DMARC, MITRE, CVE/KEV, risk_score. No key.
• io.github.dizzlkheinz/ynab-mcpb — last commit 2026-07-29, shares mcpb
  Local-first YNAB MCP for reconciliation, receipt splitting, safe cleanup, and spending analysis
• Help Scout MCP Server — last commit 2026-08-01, shares mcpb
  Search Help Scout conversations, customers, organizations, threads, and inboxes with AI assistants
• ai.aliengiraffe/spotdb — last commit 2026-08-05, shares duckdb
  Ephemeral data sandbox for AI workflows with guardrails and security

These share tags the maintainers applied themselves, such as claude-desktop, huggingface, digital-humanities, mcpb. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

How the author describes it

Topics the maintainer set on GitHub: african-studies, claude-desktop, digital-archive, digital-humanities, duckdb, huggingface, islam, islamic-studies, mcp-server, mcpb, model-context-protocol, research-data, typescript, west-africa.