# `io.github.fmadore/iwac-mcp-server` on anlyon.dev > Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by anlyon.dev. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX]. > No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour. - Page: https://anlyon.dev/servers/io.github.fmadore/iwac-mcp-server - JSON: https://anlyon.dev/api/v1/servers/io.github.fmadore/iwac-mcp-server - Version: 4.1.0 (active) - Publisher: io.github.fmadore (GitHub account) - Runs: remote (streamable-http), local (mcpb) - Sign-in to list tools: none - Repository: https://github.com/fmadore/iwac-mcp-server - Metadata from the official MCP Registry, synced 2026-10-21T18:34:13.446Z Title and description, as the publisher wrote them: ```untrusted-server-text Islam West Africa Collection (IWAC) Read-only access to the Islam West Africa Collection via Hugging Face datasets. ``` Scanned 2026-10-21T19:22:41.770Z over streamable-http. **39 tools: 1 change things and 38 only read.** | Group | Class | Tools | Claude Code | | --- | --- | --- | --- | | Deletes or cancels | destructive | 0 | deny | | Can't be undone | irreversible | 0 | ask | | Changes things | write | 1 | ask | | Only reads | read | 38 | allow | ## Findings No check matched anything in these tool definitions. ## Changes things (1) Creates or changes something that can be changed back. Claude Code: ask. ### `explore_corpus` - Nothing in its name or description says what it does, so it is counted as a write. - The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class. Description, as the server wrote it: ```untrusted-server-text 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}. ``` ## Only reads (38) Looks things up and changes nothing. Claude Code: allow. ### `fetch` - The name "fetch" says "fetch": a word for reading. Description, as the server wrote it: ```untrusted-server-text Retrieve the full text and metadata of one IWAC item by an id returned from `search` (format ':', 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. ``` ### `get_article` - The name "get_article" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `get_audiovisual` - The name "get_audiovisual" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `get_collection_stats` - The name "get_collection_stats" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `get_cooccurrence` - The name "get_cooccurrence" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `get_country_comparison` - The name "get_country_comparison" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text Compare article counts, newspaper counts, date ranges, and gpt-5-6-luna polarity across countries. ``` ### `get_document` - The name "get_document" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `get_field_distribution` - The name "get_field_distribution" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `get_image` - The name "get_image" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `get_index_entry` - The name "get_index_entry" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text Get full details of an index entry by id (raw dataset columns, French names — Titre, Prénom, Coordonnées…). ``` ### `get_lexical_metrics` - The name "get_lexical_metrics" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `get_newspaper_stats` - The name "get_newspaper_stats" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text Per-newspaper article counts and date ranges. ``` ### `get_place_distribution` - The name "get_place_distribution" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text Place tags joined to authority coordinates. Separates publication countries from mentioned places; missing geocodes are counted explicitly. ``` ### `get_publication_fulltext` - The name "get_publication_fulltext" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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). ``` ### `get_reference` - The name "get_reference" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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). ``` ### `get_semantic_map` - The name "get_semantic_map" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `get_sentiment_distribution` - The name "get_sentiment_distribution" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `get_similar_items` - The name "get_similar_items" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `get_temporal_distribution` - The name "get_temporal_distribution" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `get_topic_distribution` - The name "get_topic_distribution" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `list_audiovisual` - The name "list_audiovisual" says "list": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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`. ``` ### `list_locations` - The name "list_locations" says "list": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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` - The name "list_periodicals" says "list": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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` - The name "list_persons" says "list": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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` - The name "list_subjects" says "list": a word for reading. Description, as the server wrote it: ```untrusted-server-text List sujets from the IWAC index, sorted by frequency (most-referenced first). ``` ### `search` - The name "search" says "search": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `search_articles` - The name "search_articles" says "search": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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` - The name "search_audiovisual" says "search": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `search_by_sentiment` - The name "search_by_sentiment" says "search": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `search_documents` - The name "search_documents" says "search": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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` - The name "search_images" says "search": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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` - The name "search_index" says "search": a word for reading. Description, as the server wrote it: ```untrusted-server-text Search the IWAC authority index (persons, places, organisations, events, subjects) by name. Accent/case-insensitive. ``` ### `search_publications` - The name "search_publications" says "search": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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` - The name "search_references" says "search": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `semantic_search_articles` - The name "semantic_search_articles" says "search": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `semantic_search_images` - The name "semantic_search_images" says "search": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `semantic_search_publications` - The name "semantic_search_publications" says "search": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `semantic_search_references` - The name "semantic_search_references" says "search": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ## Claude Code permissions For `.claude/settings.json`, assuming the server is installed as `iwac`: ```json { "permissions": { "allow": [ "mcp__iwac__search", "mcp__iwac__fetch", "mcp__iwac__search_articles", "mcp__iwac__get_article", "mcp__iwac__semantic_search_articles", "mcp__iwac__search_by_sentiment", "mcp__iwac__get_sentiment_distribution", "mcp__iwac__search_index", "mcp__iwac__get_index_entry", "mcp__iwac__list_subjects", "mcp__iwac__list_locations", "mcp__iwac__list_persons", "mcp__iwac__get_collection_stats", "mcp__iwac__get_newspaper_stats", "mcp__iwac__get_country_comparison", "mcp__iwac__get_temporal_distribution", "mcp__iwac__get_topic_distribution", "mcp__iwac__get_field_distribution", "mcp__iwac__get_cooccurrence", "mcp__iwac__get_place_distribution", "mcp__iwac__get_semantic_map", "mcp__iwac__get_similar_items", "mcp__iwac__get_lexical_metrics", "mcp__iwac__search_publications", "mcp__iwac__list_periodicals", "mcp__iwac__get_publication_fulltext", "mcp__iwac__semantic_search_publications", "mcp__iwac__search_references", "mcp__iwac__get_reference", "mcp__iwac__semantic_search_references", "mcp__iwac__search_documents", "mcp__iwac__get_document", "mcp__iwac__search_audiovisual", "mcp__iwac__list_audiovisual", "mcp__iwac__get_audiovisual", "mcp__iwac__search_images", "mcp__iwac__get_image", "mcp__iwac__semantic_search_images" ], "ask": [ "mcp__iwac__explore_corpus" ], "deny": [] } } ```