iwac-mcp-server

endpoint

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

protocol

http-sse ·2025-06-18

authentication

none observed

public key

none — nobody has proven they own this listing · is it yours? claim it

karma

0 · newcomer

Is iwac-mcp-server live?

Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.

Is iwac-mcp-server free to use?

Yes — the hub reached it with no key and no payment.

What tools does iwac-mcp-server have?

39 tools: get_audiovisual, search_index, get_publication_fulltext, get_reference, get_index_entry, search, fetch, get_article, ….

Is iwac-mcp-server safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

• get_country_comparison reads open 21h ago

  Compare article counts, newspaper counts, date ranges, and claude-haiku-5-5 polarity across countries.

  mcp-tool

  123456

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {},
    "additionalProperties": false
  }

  arguments 6 lines copy
• get_place_distribution reads open 10h ago

  Place tags joined to authority coordinates. Separates publication countries from mentioned places; missing geocodes are counted explicitly.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "exact": {
        "type": "object",
        "description": "AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 20,
          "minItems": 1
        }
      },
      "top_n": {
        "type": "integer",
        "description": "Geocoded places returned (default 60, max 200)"
      },
      "subset": {
        "type": "string",
        "description": "articles (default) | publications | references"
      },
      "country": {
        "type": "string",
        "description": "Exact country name (accents optional)"
      },
      "date_to": {
        "type": "string"
      },
      "keyword": {
        "type": "string",
        "minLength": 1
      },
      "subject": {
        "type": "string",
        "description": "Exact tag"
      },
      "date_from": {
        "type": "string",
        "description": "Inclusive date bounds: YYYY[-MM[-DD]]"
      },
      "newspaper": {
        "type": "string",
        "description": "Newspaper/periodical substring"
      },
      "hijri_year": {
        "type": "integer"
      },
      "hijri_month": {
        "type": "string"
      },
      "keyword_mode": {
        "enum": [
          "literal",
          "all_terms"
        ],
        "type": "string",
        "description": "literal: the whole keyword as one substring"
      },
      "keyword_aliases": {
        "type": "array",
        "items": {
          "type": "string",
          "minLength": 1
        },
        "maxItems": 12
      }
    },
    "additionalProperties": false
  }

  arguments 75 lines copy
• list_subjects reads open 13h ago

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

  mcp-tool

  1234567891011121314

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "limit": {
        "type": "integer",
        "description": "Default 50, max 200"
      },
      "offset": {
        "type": "integer"
      }
    },
    "additionalProperties": false
  }

  arguments 14 lines copy
• get_sentiment_distribution reads open 2h ago

  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.

  mcp-tool

  12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "exact": {
        "type": "object",
        "description": "AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 20,
          "minItems": 1
        }
      },
      "model": {
        "type": "string",
        "description": "gpt-5-6-luna | mistral-small-2603 | deepseek-v4-flash-0731 | gemma-4-31b-it | qwen3-8-27b | claude-haiku-5-5 | all | consensus; default claude-haiku-5-5. Vendor aliases accepted; retired models rejected."
      },
      "country": {
        "type": "string",
        "description": "Exact country name (accents optional)"
      },
      "date_to": {
        "type": "string"
      },
      "keyword": {
        "type": "string",
        "minLength": 1
      },
      "subject": {
        "type": "string",
        "description": "Exact tag"
      },
      "date_from": {
        "type": "string",
        "description": "Inclusive date bounds: YYYY[-MM[-DD]]"
      },
      "newspaper": {
        "type": "string",
        "description": "Newspaper/periodical substring"
      },
      "hijri_year": {
        "type": "integer"
      },
      "hijri_month": {
        "type": "string"
      },
      "keyword_mode": {
        "enum": [
          "literal",
          "all_terms"
        ],
        "type": "string",
        "description": "literal: the whole keyword as one substring"
      },
      "compare_models": {
        "type": "array",
        "items": false,
        "maxItems": 2,
        "minItems": 2,
        "description": "Pair of model IDs or aliases; requires model:\"all\"",
        "prefixItems": [
          {
            "type": "string"
          },
          {
            "type": "string"
          }
        ]
      },
      "agreement_field": {
        "enum": [
          "polarity",
          "centrality",
          "subjectivity"
        ],
        "type": "string"
      },
      "keyword_aliases": {
        "type": "array",
        "items": {
          "type": "string",
          "minLength": 1
        },
        "maxItems": 12
      }
    },
    "additionalProperties": false
  }

  arguments 94 lines copy
• get_lexical_metrics reads open 17h ago

  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.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "exact": {
        "type": "object",
        "description": "AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 20,
          "minItems": 1
        }
      },
      "top_n": {
        "type": "integer",
        "description": "Groups returned when grouping by newspaper (default 20, max 60)"
      },
      "country": {
        "type": "string",
        "description": "Exact country name (accents optional)"
      },
      "date_to": {
        "type": "string"
      },
      "keyword": {
        "type": "string",
        "minLength": 1
      },
      "subject": {
        "type": "string",
        "description": "Exact tag"
      },
      "group_by": {
        "type": "string",
        "description": "year (default) | newspaper | country"
      },
      "date_from": {
        "type": "string",
        "description": "Inclusive date bounds: YYYY[-MM[-DD]]"
      },
      "newspaper": {
        "type": "string",
        "description": "Newspaper/periodical substring"
      },
      "hijri_year": {
        "type": "integer"
      },
      "hijri_month": {
        "type": "string"
      },
      "keyword_mode": {
        "enum": [
          "literal",
          "all_terms"
        ],
        "type": "string",
        "description": "literal: the whole keyword as one substring"
      },
      "keyword_aliases": {
        "type": "array",
        "items": {
          "type": "string",
          "minLength": 1
        },
        "maxItems": 12
      }
    },
    "additionalProperties": false
  }

  arguments 75 lines copy
• list_persons reads open 17h ago

  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 reaches only the few entries its references mention (index frequency counts articles, publications and references; no article is Nigerian).

  mcp-tool

  123456789101112131415161718

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "limit": {
        "type": "integer",
        "description": "Default 50, max 200"
      },
      "offset": {
        "type": "integer"
      },
      "country": {
        "type": "string",
        "description": "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"
      }
    },
    "additionalProperties": false
  }

  arguments 18 lines copy
• search_audiovisual reads open 10h ago

  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.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "limit": {
        "type": "integer",
        "description": "Default 20, max 50"
      },
      "medium": {
        "type": "string",
        "description": "Exact carrier medium: Vidéo sur le web | DVD | CD (validated, accents optional)"
      },
      "offset": {
        "type": "integer"
      },
      "country": {
        "type": "string",
        "description": "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": {
        "type": "string",
        "description": "Every word must occur across the title/metadata fields; \"quote\" a phrase"
      },
      "subject": {
        "type": "string",
        "description": "Exact subject tag — only ~27 rows carry one, so prefer publisher/keyword"
      },
      "language": {
        "type": "string",
        "description": "Exact language value, e.g. Français | Haoussa | Arabe | Anglais | Mooré"
      },
      "publisher": {
        "type": "string",
        "description": "Substring on the publishing channel/broadcaster, e.g. RTB | AEEM | CERFI"
      },
      "source_type": {
        "type": "string",
        "description": "youtube (harvested web video, the large majority) | deposited (recordings with a file, 47)"
      }
    },
    "additionalProperties": false
  }

  arguments 42 lines copy
• search_by_sentiment reads open 10h ago

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

  mcp-tool

  12345678910111213141516171819202122232425262728293031323334353637

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "limit": {
        "type": "integer",
        "description": "Default 20, max 100"
      },
      "offset": {
        "type": "integer"
      },
      "country": {
        "type": "string",
        "description": "Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Togo (accents optional)"
      },
      "subject": {
        "type": "string"
      },
      "disputed": {
        "type": "string",
        "description": "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": {
        "type": "string",
        "description": "Très positif | Positif | Neutre | Négatif | Très négatif | Non applicable"
      },
      "centrality": {
        "type": "string",
        "description": "Très central | Central | Secondaire | Marginal | Non abordé"
      },
      "subjectivity": {
        "type": "string",
        "description": "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."
      }
    },
    "additionalProperties": false
  }

  arguments 37 lines copy
• get_semantic_map open 2h ago

  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.

  mcp-tool

  12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "exact": {
        "type": "object",
        "description": "AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 20,
          "minItems": 1
        }
      },
      "limit": {
        "type": "integer",
        "description": "Items projected (default 300, max 2000)"
      },
      "subset": {
        "type": "string",
        "description": "articles (default) | documents | publications | references"
      },
      "country": {
        "type": "string",
        "description": "Exact country name (accents optional)"
      },
      "date_to": {
        "type": "string"
      },
      "keyword": {
        "type": "string",
        "minLength": 1
      },
      "subject": {
        "type": "string",
        "description": "Exact tag"
      },
      "color_by": {
        "type": "string",
        "description": "country | newspaper | subject | lda_topic_label | polarity (claude-haiku-5-5's label)"
      },
      "date_from": {
        "type": "string",
        "description": "Inclusive date bounds: YYYY[-MM[-DD]]"
      },
      "newspaper": {
        "type": "string",
        "description": "Newspaper/periodical substring"
      },
      "hijri_year": {
        "type": "integer"
      },
      "hijri_month": {
        "type": "string"
      },
      "keyword_mode": {
        "enum": [
          "literal",
          "all_terms"
        ],
        "type": "string",
        "description": "literal: the whole keyword as one substring"
      },
      "keyword_aliases": {
        "type": "array",
        "items": {
          "type": "string",
          "minLength": 1
        },
        "maxItems": 12
      }
    },
    "additionalProperties": false
  }

  arguments 79 lines copy
• get_temporal_distribution open 28h ago

  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.

  mcp-tool

  12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "exact": {
        "type": "object",
        "description": "AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 20,
          "minItems": 1
        }
      },
      "subset": {
        "type": "string",
        "description": "articles (default) | publications | references | documents | audiovisual | images"
      },
      "country": {
        "type": "string",
        "description": "Exact country name (accents optional)"
      },
      "date_to": {
        "type": "string"
      },
      "keyword": {
        "type": "string",
        "minLength": 1
      },
      "subject": {
        "type": "string",
        "description": "Exact tag"
      },
      "calendar": {
        "type": "string",
        "description": "gregorian (default) | hijri — bucket by the Islamic (Umm al-Qura) calendar"
      },
      "group_by": {
        "type": "string",
        "description": "country | newspaper — one distribution per group value"
      },
      "date_from": {
        "type": "string",
        "description": "Inclusive date bounds: YYYY[-MM[-DD]]"
      },
      "newspaper": {
        "type": "string",
        "description": "Newspaper/periodical substring"
      },
      "hijri_year": {
        "type": "integer"
      },
      "granularity": {
        "type": "string",
        "description": "year (default) | month | lunar_month (all years collapsed into 12 lunar months; needs calendar=hijri)"
      },
      "hijri_month": {
        "type": "string"
      },
      "keyword_mode": {
        "enum": [
          "literal",
          "all_terms"
        ],
        "type": "string",
        "description": "literal: the whole keyword as one substring"
      },
      "normalize_by": {
        "enum": [
          "scope",
          "searchable"
        ],
        "type": "string",
        "description": "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": {
        "type": "array",
        "items": {
          "type": "string",
          "minLength": 1
        },
        "maxItems": 12
      }
    },
    "additionalProperties": false
  }

  arguments 91 lines copy
• search_articles open 13h ago

  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.

  mcp-tool

  12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "exact": {
        "type": "object",
        "description": "AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 20,
          "minItems": 1
        }
      },
      "limit": {
        "type": "integer",
        "description": "Default 20, max 100 (10 and 25 with with_description)"
      },
      "offset": {
        "type": "integer"
      },
      "country": {
        "type": "string",
        "description": "Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Togo (accents optional)"
      },
      "date_to": {
        "type": "string",
        "description": "YYYY-MM-DD (or YYYY)"
      },
      "keyword": {
        "type": "string",
        "description": "Concept keyword; every word must occur (any order) in the title, OCR or French/English AI abstracts; \"quote\" a phrase. Prefer French for the OCR; an English term still matches via the English abstract"
      },
      "subject": {
        "type": "string"
      },
      "date_from": {
        "type": "string",
        "description": "YYYY-MM-DD (or YYYY)"
      },
      "newspaper": {
        "type": "string"
      },
      "hijri_year": {
        "type": "integer",
        "description": "Islamic (Umm al-Qura) year, e.g. 1445"
      },
      "hijri_month": {
        "type": "string",
        "description": "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": {
        "enum": [
          "literal",
          "all_terms"
        ],
        "type": "string",
        "description": "literal: the whole keyword as one substring"
      },
      "keyword_aliases": {
        "type": "array",
        "items": {
          "type": "string",
          "minLength": 1
        },
        "maxItems": 12
      },
      "with_description": {
        "type": "boolean",
        "description": "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."
      }
    },
    "additionalProperties": false
  }

  arguments 79 lines copy
• get_collection_stats open 2h ago

  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.

  mcp-tool

  123456

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {},
    "additionalProperties": false
  }

  arguments 6 lines copy
• list_audiovisual reads open 21h ago

  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`.

  mcp-tool

  1234567891011121314151617181920212223242526

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "limit": {
        "type": "integer",
        "description": "Default 20, max 50"
      },
      "offset": {
        "type": "integer"
      },
      "country": {
        "type": "string",
        "description": "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": {
        "type": "string",
        "description": "Substring on the publishing channel/broadcaster, e.g. RTB | AEEM | CERFI"
      },
      "source_type": {
        "type": "string",
        "description": "youtube (harvested web video, the large majority) | deposited (recordings with a file, 47)"
      }
    },
    "additionalProperties": false
  }

  arguments 26 lines copy
• get_topic_distribution reads open 24h ago

  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.

  mcp-tool

  1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "exact": {
        "type": "object",
        "description": "AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 20,
          "minItems": 1
        }
      },
      "top_n": {
        "type": "integer",
        "description": "Topics given their own band in over_time (default 8, max 15)"
      },
      "subset": {
        "type": "string",
        "description": "articles (default) | references"
      },
      "country": {
        "type": "string",
        "description": "Exact country name (accents optional)"
      },
      "date_to": {
        "type": "string"
      },
      "keyword": {
        "type": "string",
        "minLength": 1
      },
      "subject": {
        "type": "string",
        "description": "Exact tag"
      },
      "min_prob": {
        "type": "number",
        "description": "0-1; keep only assignments at or above this probability"
      },
      "date_from": {
        "type": "string",
        "description": "Inclusive date bounds: YYYY[-MM[-DD]]"
      },
      "newspaper": {
        "type": "string",
        "description": "Newspaper/periodical substring"
      },
      "over_time": {
        "type": "boolean",
        "description": "Also return per-year counts for the leading topics"
      },
      "hijri_year": {
        "type": "integer"
      },
      "hijri_month": {
        "type": "string"
      },
      "keyword_mode": {
        "enum": [
          "literal",
          "all_terms"
        ],
        "type": "string",
        "description": "literal: the whole keyword as one substring"
      },
      "keyword_aliases": {
        "type": "array",
        "items": {
          "type": "string",
          "minLength": 1
        },
        "maxItems": 12
      }
    },
    "additionalProperties": false
  }

  arguments 83 lines copy
• get_newspaper_stats open 13h ago

  Per-newspaper article counts and date ranges.

  mcp-tool

  1234567891011

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "country": {
        "type": "string",
        "description": "Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Togo (accents optional)"
      }
    },
    "additionalProperties": false
  }

  arguments 11 lines copy
• get_cooccurrence reads open 24h ago

  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.

  mcp-tool

  12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "exact": {
        "type": "object",
        "description": "AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 20,
          "minItems": 1
        }
      },
      "field": {
        "type": "string",
        "description": "subject (default) | spatial | author | language"
      },
      "top_n": {
        "type": "integer",
        "description": "Values on each axis (default 15, max 30)"
      },
      "subset": {
        "type": "string",
        "description": "articles (default) | publications | references"
      },
      "country": {
        "type": "string",
        "description": "Exact country name (accents optional)"
      },
      "date_to": {
        "type": "string"
      },
      "keyword": {
        "type": "string",
        "minLength": 1
      },
      "subject": {
        "type": "string",
        "description": "Exact tag"
      },
      "date_from": {
        "type": "string",
        "description": "Inclusive date bounds: YYYY[-MM[-DD]]"
      },
      "newspaper": {
        "type": "string",
        "description": "Newspaper/periodical substring"
      },
      "hijri_year": {
        "type": "integer"
      },
      "hijri_month": {
        "type": "string"
      },
      "keyword_mode": {
        "enum": [
          "literal",
          "all_terms"
        ],
        "type": "string",
        "description": "literal: the whole keyword as one substring"
      },
      "keyword_aliases": {
        "type": "array",
        "items": {
          "type": "string",
          "minLength": 1
        },
        "maxItems": 12
      }
    },
    "additionalProperties": false
  }

  arguments 79 lines copy
• search_publications reads open 28h ago

  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.

  mcp-tool

  1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "exact": {
        "type": "object",
        "description": "AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 20,
          "minItems": 1
        }
      },
      "limit": {
        "type": "integer",
        "description": "Default 20, max 100"
      },
      "offset": {
        "type": "integer"
      },
      "country": {
        "type": "string",
        "description": "Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Togo (accents optional)"
      },
      "date_to": {
        "type": "string",
        "description": "Latest year, YYYY"
      },
      "keyword": {
        "type": "string",
        "description": "French concept keyword; every word must occur in the title, subject, table of contents or OCR; \"quote\" a phrase"
      },
      "subject": {
        "type": "string",
        "description": "Subject tag (~87% of issues are tagged)"
      },
      "date_from": {
        "type": "string",
        "description": "Earliest year, YYYY"
      },
      "newspaper": {
        "type": "string",
        "description": "Periodical/series title (see list_periodicals)"
      },
      "hijri_year": {
        "type": "integer",
        "description": "Islamic (Umm al-Qura) year, e.g. 1445"
      },
      "hijri_month": {
        "type": "string",
        "description": "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": {
        "enum": [
          "literal",
          "all_terms"
        ],
        "type": "string",
        "description": "literal: the whole keyword as one substring"
      },
      "keyword_aliases": {
        "type": "array",
        "items": {
          "type": "string",
          "minLength": 1
        },
        "maxItems": 12
      }
    },
    "additionalProperties": false
  }

  arguments 77 lines copy
• list_periodicals open 17h ago

  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.

  mcp-tool

  1234567891011

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "country": {
        "type": "string",
        "description": "Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Togo (accents optional)"
      }
    },
    "additionalProperties": false
  }

  arguments 11 lines copy
• search_references open 24h ago

  Search academic references (journal articles, book chapters, theses, books, reports) by keyword and metadata. `keyword` requires every word in the title + abstract ("quote" a phrase). 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.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "limit": {
        "type": "integer",
        "description": "Default 20, max 100"
      },
      "author": {
        "type": "string"
      },
      "offset": {
        "type": "integer"
      },
      "country": {
        "type": "string",
        "description": "Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Nigeria | Togo (accents optional)"
      },
      "date_to": {
        "type": "string",
        "description": "Latest year, YYYY"
      },
      "keyword": {
        "type": "string",
        "description": "French or English concept keyword; every word must occur in the title + abstract; \"quote\" a phrase"
      },
      "subject": {
        "type": "string",
        "description": "Subject tag (sparse: ~27% of references are tagged)"
      },
      "language": {
        "type": "string",
        "description": "e.g. Français | Anglais"
      },
      "date_from": {
        "type": "string",
        "description": "Earliest year, YYYY"
      },
      "reference_type": {
        "type": "string",
        "description": "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'."
      }
    },
    "additionalProperties": false
  }

  arguments 45 lines copy
• search_images open 6h ago

  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.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "limit": {
        "type": "integer",
        "description": "Default 20, max 50"
      },
      "offset": {
        "type": "integer"
      },
      "country": {
        "type": "string",
        "description": "Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Nigeria | Togo (accents optional)"
      },
      "creator": {
        "type": "string",
        "description": "Photographer name (substring match)"
      },
      "date_to": {
        "type": "string",
        "description": "YYYY-MM-DD (or YYYY)"
      },
      "keyword": {
        "type": "string",
        "description": "French concept keyword; every word must occur in the title, creator, subject, place or caption; \"quote\" a phrase"
      },
      "spatial": {
        "type": "string",
        "description": "Exact place name, e.g. Ouagadougou (pipe-aware)"
      },
      "subject": {
        "type": "string",
        "description": "Exact subject tag (pipe-aware)"
      },
      "date_from": {
        "type": "string",
        "description": "YYYY-MM-DD (or YYYY)"
      }
    },
    "additionalProperties": false
  }

  arguments 42 lines copy
• list_locations reads open 21h ago

  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 reaches only the few entries its references mention (index frequency counts articles, publications and references; no article is Nigerian).

  mcp-tool

  123456789101112131415161718

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "limit": {
        "type": "integer",
        "description": "Default 50, max 200"
      },
      "offset": {
        "type": "integer"
      },
      "country": {
        "type": "string",
        "description": "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"
      }
    },
    "additionalProperties": false
  }

  arguments 18 lines copy
• search_documents reads open 6h ago

  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.

  mcp-tool

  12345678910111213141516171819202122

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "limit": {
        "type": "integer",
        "description": "Default 15, max 50"
      },
      "offset": {
        "type": "integer"
      },
      "country": {
        "type": "string",
        "description": "Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Nigeria | Togo (accents optional). Corpus is mostly Burkina Faso/Togo/Benin"
      },
      "keyword": {
        "type": "string",
        "description": "Concept keyword; every word must occur in the title, OCR, French/English AI descriptions or subject; \"quote\" a phrase"
      }
    },
    "additionalProperties": false
  }

  arguments 22 lines copy
• explore_corpus open 6h ago

  Selection workbench: items, concordance, coverage, compare (requires comparison), attention, aliases, or paginated manifest/CSL-JSON/BibTeX exports. Exact filters intersect. limit/offset also page compare/coverage/attention cells. Coverage measures archive availability. Exports identify this page and dataset snapshot; compare snapshot IDs across pages. Schema discovery: iwac://datasets/{subset}.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "link": {
        "type": "boolean",
        "description": "Export modes: link the whole selection (≤5000) as one file instead of a page"
      },
      "mode": {
        "enum": [
          "items",
          "concordance",
          "coverage",
          "compare",
          "attention",
          "aliases",
          "manifest",
          "csl_json",
          "bibtex"
        ],
        "type": "string",
        "default": "items"
      },
      "limit": {
        "type": "integer",
        "default": 20,
        "maximum": 50,
        "minimum": 1
      },
      "offset": {
        "type": "integer",
        "default": 0,
        "minimum": 0
      },
      "subset": {
        "enum": [
          "articles",
          "publications",
          "documents",
          "audiovisual",
          "images",
          "index",
          "references"
        ],
        "type": "string",
        "default": "articles"
      },
      "selection": {
        "type": "object",
        "properties": {
          "exact": {
            "type": "object",
            "description": "AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {
              "type": "array",
              "items": {
                "type": "string"
              },
              "maxItems": 20,
              "minItems": 1
            }
          },
          "country": {
            "type": "string",
            "description": "Exact country name (accents optional)"
          },
          "date_to": {
            "type": "string"
          },
          "keyword": {
            "type": "string",
            "minLength": 1
          },
          "subject": {
            "type": "string",
            "description": "Exact tag"
          },
          "date_from": {
            "type": "string",
            "description": "Inclusive date bounds: YYYY[-MM[-DD]]"
          },
          "newspaper": {
            "type": "string",
            "description": "Newspaper/periodical substring"
          },
          "hijri_year": {
            "type": "integer"
          },
          "hijri_month": {
            "type": "string"
          },
          "keyword_mode": {
            "enum": [
              "literal",
              "all_terms"
            ],
            "type": "string",
            "description": "literal: the whole keyword as one substring"
          },
          "keyword_aliases": {
            "type": "array",
            "items": {
              "type": "string",
              "minLength": 1
            },
            "maxItems": 12
          }
        },
        "additionalProperties": false
      },
      "comparison": {
        "type": "object",
        "properties": {
          "exact": {
            "type": "object",
            "description": "AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {
              "type": "array",
              "items": {
                "type": "string"
              },
              "maxItems": 20,
              "minItems": 1
            }
          },
          "country": {
            "type": "string",
            "description": "Exact country name (accents optional)"
          },
          "date_to": {
            "type": "string"
          },
          "keyword": {
            "type": "string",
            "minLength": 1
          },
          "subject": {
            "type": "string",
            "description": "Exact tag"
          },
          "date_from": {
            "type": "string",
            "description": "Inclusive date bounds: YYYY[-MM[-DD]]"
          },
          "newspaper": {
            "type": "string",
            "description": "Newspaper/periodical substring"
          },
          "hijri_year": {
            "type": "integer"
          },
          "hijri_month": {
            "type": "string"
          },
          "keyword_mode": {
            "enum": [
              "literal",
              "all_terms"
            ],
            "type": "string",
            "description": "literal: the whole keyword as one substring"
          },
          "keyword_aliases": {
            "type": "array",
            "items": {
              "type": "string",
              "minLength": 1
            },
            "maxItems": 12
          }
        },
        "additionalProperties": false
      }
    },
    "additionalProperties": false
  }

  arguments 182 lines copy
• get_audiovisual reads unknown 45h ago

  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.

  mcp-tool

  1234567891011121314151617181920

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "audiovisual_id"
    ],
    "properties": {
      "offset": {
        "type": "integer",
        "description": "Read from this character on: the previous part's next_offset"
      },
      "keyword": {
        "type": "string"
      },
      "audiovisual_id": {
        "type": "integer"
      }
    },
    "additionalProperties": false
  }

  arguments 20 lines copy
• search_index reads unknown 2d ago

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

  mcp-tool

  12345678910111213141516171819202122232425

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "keyword"
    ],
    "properties": {
      "limit": {
        "type": "integer",
        "description": "Default 20, max 100"
      },
      "offset": {
        "type": "integer"
      },
      "keyword": {
        "type": "string",
        "description": "Every word must occur in the entry title (any order); \"quote\" a phrase, or give a whole alternate title"
      },
      "index_type": {
        "type": "string",
        "description": "Exact type (accents optional), validated against: Personnes | Lieux | Organisations | Événements | Sujets | Notices d'autorité. An unrecognised value returns an error listing the valid types."
      }
    },
    "additionalProperties": false
  }

  arguments 25 lines copy
• get_publication_fulltext reads unknown 2d ago

  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).

  mcp-tool

  12345678910111213141516171819202122232425262728

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "publication_id"
    ],
    "properties": {
      "offset": {
        "type": "integer",
        "description": "Read from this character on: the previous part's next_offset"
      },
      "keyword": {
        "type": "string"
      },
      "max_excerpts": {
        "type": "integer",
        "description": "Default 10, max 25"
      },
      "context_chars": {
        "type": "integer",
        "description": "Default 2000, max 5000"
      },
      "publication_id": {
        "type": "integer"
      }
    },
    "additionalProperties": false
  }

  arguments 28 lines copy
• get_reference reads unknown 2d ago

  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).

  mcp-tool

  12345678910111213

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "reference_id"
    ],
    "properties": {
      "reference_id": {
        "type": "integer"
      }
    },
    "additionalProperties": false
  }

  arguments 13 lines copy
• get_index_entry reads unknown 2d ago

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

  mcp-tool

  12345678910111213

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "entry_id"
    ],
    "properties": {
      "entry_id": {
        "type": "integer"
      }
    },
    "additionalProperties": false
  }

  arguments 13 lines copy
• search reads unknown 2d ago

  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.

  mcp-tool

  12345678910111213141516171819

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "query"
    ],
    "properties": {
      "limit": {
        "type": "integer",
        "description": "Max results across all categories. Default 20, max 50."
      },
      "query": {
        "type": "string",
        "minLength": 1,
        "description": "One concept, name, or short phrase; use French concept terms for primary sources, and French/English terms for references"
      }
    },
    "additionalProperties": false
  }

  arguments 19 lines copy
• fetch reads unknown 2d ago

  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.

  mcp-tool

  1234567891011121314

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "id"
    ],
    "properties": {
      "id": {
        "type": "string",
        "description": "Item id from search, e.g. 'articles:28576' or 'references:11045'"
      }
    },
    "additionalProperties": false
  }

  arguments 14 lines copy
• get_article reads unknown 2d ago

  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.

  mcp-tool

  1234567891011121314151617181920212223242526272829

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "article_id"
    ],
    "properties": {
      "offset": {
        "type": "integer",
        "description": "Read from this character on: the previous part's next_offset"
      },
      "keyword": {
        "type": "string",
        "description": "Return excerpts around matches instead of the full OCR (accent-insensitive)"
      },
      "article_id": {
        "type": "integer"
      },
      "max_excerpts": {
        "type": "integer",
        "description": "Default 10, max 25"
      },
      "context_chars": {
        "type": "integer",
        "description": "Default 2000, max 5000"
      }
    },
    "additionalProperties": false
  }

  arguments 29 lines copy
• semantic_search_articles unknown 2d ago

  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.

  mcp-tool

  1234567891011121314151617181920212223242526272829303132333435

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "query"
    ],
    "properties": {
      "limit": {
        "type": "integer",
        "description": "Default 10, max 50"
      },
      "query": {
        "type": "string",
        "maxLength": 8192,
        "minLength": 1,
        "description": "Natural-language query, any language"
      },
      "country": {
        "type": "string",
        "description": "Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Togo (accents optional)"
      },
      "date_to": {
        "type": "string",
        "description": "YYYY-MM-DD (or YYYY)"
      },
      "date_from": {
        "type": "string",
        "description": "YYYY-MM-DD (or YYYY)"
      },
      "newspaper": {
        "type": "string"
      }
    },
    "additionalProperties": false
  }

  arguments 35 lines copy
• get_field_distribution unknown 2d ago

  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.

  mcp-tool

  1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "field"
    ],
    "properties": {
      "exact": {
        "type": "object",
        "description": "AND values. Fields: subject/spatial/author/language/country/newspaper/topic_id/min_prob/scored_by; country_raw=whole cell; polarity:<model>.",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 20,
          "minItems": 1
        }
      },
      "field": {
        "type": "string",
        "description": "subject | spatial | author | language | newspaper | country"
      },
      "top_n": {
        "type": "integer",
        "description": "Values returned (default 25, max 100)"
      },
      "subset": {
        "type": "string",
        "description": "articles (default) | publications | references"
      },
      "country": {
        "type": "string",
        "description": "Exact country name (accents optional)"
      },
      "date_to": {
        "type": "string"
      },
      "keyword": {
        "type": "string",
        "minLength": 1
      },
      "subject": {
        "type": "string",
        "description": "Exact tag"
      },
      "date_from": {
        "type": "string",
        "description": "Inclusive date bounds: YYYY[-MM[-DD]]"
      },
      "newspaper": {
        "type": "string",
        "description": "Newspaper/periodical substring"
      },
      "over_time": {
        "type": "boolean",
        "description": "Also return the per-year share of items carrying a value"
      },
      "hijri_year": {
        "type": "integer"
      },
      "hijri_month": {
        "type": "string"
      },
      "keyword_mode": {
        "enum": [
          "literal",
          "all_terms"
        ],
        "type": "string",
        "description": "literal: the whole keyword as one substring"
      },
      "keyword_aliases": {
        "type": "array",
        "items": {
          "type": "string",
          "minLength": 1
        },
        "maxItems": 12
      }
    },
    "additionalProperties": false
  }

  arguments 86 lines copy
• get_similar_items reads unknown 2d ago

  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.

  mcp-tool

  12345678910111213141516171819202122232425262728

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "id"
    ],
    "properties": {
      "id": {
        "type": "string",
        "description": "Item id — either a bare o:id ('3064') or the namespaced form search returns ('articles:3064')"
      },
      "limit": {
        "type": "integer",
        "description": "Neighbours returned (default 12, max 50)"
      },
      "subset": {
        "type": "string",
        "description": "articles (default) | documents | publications | references"
      },
      "min_score": {
        "type": "number",
        "maximum": 1,
        "minimum": -1,
        "description": "Minimum cosine similarity (-1 to 1)"
      }
    },
    "additionalProperties": false
  }

  arguments 28 lines copy
• get_document reads unknown 38h ago

  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.

  mcp-tool

  1234567891011121314151617181920212223242526272829

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "document_id"
    ],
    "properties": {
      "offset": {
        "type": "integer",
        "description": "Read from this character on: the previous part's next_offset"
      },
      "keyword": {
        "type": "string",
        "description": "Return excerpts around matches instead of the full OCR (accent-insensitive)"
      },
      "document_id": {
        "type": "integer"
      },
      "max_excerpts": {
        "type": "integer",
        "description": "Default 10, max 25"
      },
      "context_chars": {
        "type": "integer",
        "description": "Default 2000, max 5000"
      }
    },
    "additionalProperties": false
  }

  arguments 29 lines copy
• get_image reads unknown 2d ago

  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.

  mcp-tool

  12345678910111213

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "image_id"
    ],
    "properties": {
      "image_id": {
        "type": "integer"
      }
    },
    "additionalProperties": false
  }

  arguments 13 lines copy
• semantic_search_images unknown 2d ago

  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.

  mcp-tool

  123456789101112131415161718192021222324

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "query"
    ],
    "properties": {
      "limit": {
        "type": "integer",
        "description": "Default 10, max 30"
      },
      "query": {
        "type": "string",
        "maxLength": 8192,
        "minLength": 1,
        "description": "Description of the visual content, any language"
      },
      "country": {
        "type": "string",
        "description": "Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Nigeria | Togo (accents optional)"
      }
    },
    "additionalProperties": false
  }

  arguments 24 lines copy
• semantic_search_publications unknown 45h ago

  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.

  mcp-tool

  123456789101112131415161718192021222324

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "query"
    ],
    "properties": {
      "limit": {
        "type": "integer",
        "description": "Default 10, max 50"
      },
      "query": {
        "type": "string",
        "maxLength": 8192,
        "minLength": 1,
        "description": "Natural-language query, any language"
      },
      "country": {
        "type": "string",
        "description": "Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Togo (accents optional)"
      }
    },
    "additionalProperties": false
  }

  arguments 24 lines copy
• semantic_search_references unknown 45h ago

  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.

  mcp-tool

  12345678910111213141516171819202122232425262728293031323334353637383940

  {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "query"
    ],
    "properties": {
      "limit": {
        "type": "integer",
        "description": "Default 10, max 50"
      },
      "query": {
        "type": "string",
        "maxLength": 8192,
        "minLength": 1,
        "description": "Natural-language query, any language"
      },
      "country": {
        "type": "string",
        "description": "Exact country name: Benin | Burkina Faso | Côte d'Ivoire | Niger | Nigeria | Togo (accents optional)"
      },
      "date_to": {
        "type": "string",
        "description": "Latest year, YYYY"
      },
      "language": {
        "type": "string",
        "description": "e.g. Français | Anglais"
      },
      "date_from": {
        "type": "string",
        "description": "Earliest year, YYYY"
      },
      "reference_type": {
        "type": "string",
        "description": "French type label, substring (e.g. Thèse de doctorat)"
      }
    },
    "additionalProperties": false
  }

  arguments 40 lines copy

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.