Islam West Africa Collection (IWAC)
io.github.fmadore/iwac-mcp-serverRead-only access to the Islam West Africa Collection via Hugging Face datasets.
Watch this dependency
Get before/after evidence when observed tools, schemas, authentication access, availability or the endpoint changes.
Inspect evidence and set up a watch Share public evidence report
Score: 100/100
Handshake verified by our own probe.
why this score
Tools · 39
Search the Islam West Africa Collection across newspaper articles, Islamic publications, archival documents, academic references, audiovisual recordings, photographs, and the authority index (persons/…
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…
Selection workbench: items, concordance, coverage, compare (requires comparison), attention, aliases, or paginated manifest/CSL-JSON/BibTeX exports. Exact filters intersect. Coverage measures archive …
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 lan…
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 …
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…
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…
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_fiel…
Search the IWAC authority index (persons, places, organisations, events, subjects) by name. Accent/case-insensitive.
Get full details of an index entry by id (raw dataset columns, French names — Titre, Prénom, Coordonnées…).
List sujets from the IWAC index, sorted by frequency (most-referenced first).
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), rank…
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), …
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…
Per-newspaper article counts and date ranges.
Compare article counts, newspaper counts, date ranges, and gpt-5-6-luna polarity across countries.
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 de…
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 …
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/au…
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.
Place tags joined to authority coordinates. Separates publication countries from mentioned places; missing geocodes are counted explicitly.
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 a…
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-d…
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 dis…
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…
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.
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).
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…
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 (…
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).
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, Em…
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 langua…
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 …
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 reco…
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`.
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 li…
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. Ea…
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.
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 phot…
Resources · 15
Interactive charts for the IWAC statistics tools: coverage over time, periodical runs, country and newspaper comparisons, sentiment breakdowns and collection composition.
ui://iwac/charts.html
Catalogue of the 'iwac-mcp' Agent Skill served by this server: every file with its size and SHA-256 digest. Read skill://iwac-mcp/SKILL.md for the skill itself; the reference files it names are resour…
skill://iwac-mcp
Structured academic research workflow for the Islam West Africa Collection (IWAC) MCP server. Use this skill when: - Conducting research queries through the IWAC MCP server (iwac-mcp-server tools) - I…
skill://iwac-mcp/SKILL.md
iwac-mcp reference: Systematic biases and constraints to disclose when producing research outputs.
skill://iwac-mcp/references/biases-and-limitations.md
iwac-mcp reference: Source material for answering capability questions in plain language ("what can you do?", "qu'est-ce que tu peux faire ?", "what's in IWAC?", "how could I search this?"). Answer in…
skill://iwac-mcp/references/capabilities-overview.md
iwac-mcp reference: Key research domains covered by IWAC, with French search terms and transliteration variants. Use these as starting points for Phase 2 systematic searches.
skill://iwac-mcp/references/research-domains.md
iwac-mcp reference: 39 tools (4 of them semantic search, which an operator can turn off) organized by the workflow phase where they are most useful. Server v0.8.0+: all keyword/filter matching is acce…
skill://iwac-mcp/references/tools-by-phase.md
Subset schemas and reproducible export guidance
iwac://datasets
Live articles schema, available fields and snapshot provenance
iwac://datasets/articles
Live publications schema, available fields and snapshot provenance
iwac://datasets/publications
Live documents schema, available fields and snapshot provenance
iwac://datasets/documents
Live audiovisual schema, available fields and snapshot provenance
iwac://datasets/audiovisual
Live images schema, available fields and snapshot provenance
iwac://datasets/images
Live index schema, available fields and snapshot provenance
iwac://datasets/index
Live references schema, available fields and snapshot provenance
iwac://datasets/references
Prompts · 2
Run a structured, source-cited investigation of the IWAC archive at a chosen depth (brief or extended), following the five-phase method: scope, search, read, triangulate, synthesise.
A plain-language tour of what the Islam West Africa Collection holds and the kinds of questions it can answer — no research run, no tool enumeration.
Skills · 1
Structured academic research workflow for the Islam West Africa Collection (IWAC) MCP server. Use this skill when: - Conducting research queries through the IWAC MCP server (iwac-mcp-server tools) - I…
skill://iwac-mcp/SKILL.md
How to use
Add to your Claude Desktop / Cursor / Cline MCP config:
{
"mcpServers": {
"islam_west_africa_collection_(iwac)": {
"url": "https://islam.zmo.de/mcp/",
"transport": "streamable-http"
}
}
}