AMIRA — Africa Multiple Research Data

Connect it to your AI

Claude Code

claude mcp add --transport http amira-mcp-server https://data.africamultiple.uni-bayreuth.de/mcp

Claude, ChatGPT, Cursor and other apps

Add it as a custom connector with this URL (Streamable HTTP):

https://data.africamultiple.uni-bayreuth.de/mcp

Cursor, VS Code and other apps (mcp.json)

{
  "mcpServers": {
    "amira-mcp-server": {
      "url": "https://data.africamultiple.uni-bayreuth.de/mcp"
    }
  }
}

Tools it offers

35 tools, as the server itself reported during our check on Oct 31, 2026.

• get_collection_overviewStart here: corpus counts, text coverage, breakdowns, dates, snapshot freshness and refresh status.
• search_research_itemsSearch digitised research items. Filters are AND-combined; empty results suggest a filter to relax or a stored place name. export links all matches as a file.
• get_research_itemResearch-item metadata, linked entities, rights, media files, IIIF manifest and a generated citation (BibTeX/RIS/CSL-JSON). Long fields cap at 25,000 characters.
• search_projectsSearch project names, descriptions and membership. Returns cited summaries and item counts; use get_project for detail.
• get_projectProject description, team, sections, funders, item counts by type, top subjects and ten sample research items, with citation links.
• list_research_sectionsCluster research sections, funding phases, project/item counts and citation links. Includes the external-collection grouping.
• get_research_sectionOne research section's description, team and projects, each with its research-item count.
• search_personsFind canonical person authority records. Names accept either order and ignore accents. Use resolve_entity to disambiguate homonyms.
• get_personPerson affiliations, identifiers, project and section roles, credited items, publications, podcasts, videos and collaborators. Lists cap at 50 with totals. Use id to disambiguate.
• list_institutionsBrowse institution authorities by name or acronym (e.g. 'UJKZ'), with project counts and citation links.
• get_institutionInstitution or group profile: identifiers, members, funded projects and credited items, with citation links.
• list_cluster_partnersCluster partner institutions grouped by catalogue category, with citation links.
• list_groupsBrowse research groups and associations by name, with citation links.
• list_subjectsSubject headings (LCSH or free tags) ranked by distinct research-item count. Feed a heading into search_research_items.subject.
• list_locationsResearch places with coordinates and ancestor rollups. One item can count under both city and country. Feed a name into search_research_items.location.
• list_collectionsOmeka item sets ranked by research-item count, with catalogue links. Feed an ID into search_research_items.collection.
• list_categoriesRanked formats, languages or resource types used by research items. Feed values into the corresponding search filters.
• list_yearsResearch-item year/decade histogram with dated and undated counts. A date range counts in each spanned bucket. Supports shared item filters and pagination.
• search_publicationsAND-filtered bibliography, newest first. Keyword includes PDF text and returns match snippets. citation_format returns citations per page; export links every match as one file. Cite amira_url.
• get_publicationPublication metadata and citation export (BibTeX default). Full text is opt-in and paginated. Cite amira_url; DOI/repository links are additional sources.
• list_publication_facetsRanked facets for the entire filtered bibliography before pagination. Uses the same selection rules as search_publications.
• list_journalsPublication venues ranked by linked bibliography records, with ISSN and catalogue links.
• find_relatedSubjects, people, places and projects connected through shared records. Per-corpus counts deduplicate each record; subject/person seeds also include publications. Returns ambiguity and cited samples.
• search_podcastsSearch podcast metadata and transcripts. Text-only hits include snippets; full transcripts require get_podcast with opt-in.
• get_podcastPodcast detail, duration, audio file and citation link; says which model generated the transcript. Transcript is opt-in, bounded and pageable.
• search_videosSearch video metadata and transcripts. Text-only hits include snippets; full transcripts require get_video with opt-in.
• get_videoVideo detail, thumbnail and citation link; says how the transcript was produced when recorded. Transcript is opt-in, bounded and pageable.
• resolve_entityResolve a label or typed ID to cited candidates. Returns ambiguity instead of merging names. Use a returned id with get_entity_graph or get_* tools.
• get_entity_graphOne-hop graph from a typed ID: explicit catalogue links and derived co-occurrence with distinct-record counts and cited evidence. types filters neighbours before the bounds. Pass edge_id to page its evidence; pin snapsho
• get_text_passagesFind literal accent-insensitive keyword passages in selected publication/video/podcast IDs. Original UTF-16 offsets, bounded context, and citations. Requires full text exposure; no semantic ranking.
• compare_collectionsCompare 2–4 projects or item sets with identical research-item filters. Reports denominators, missingness, dates and top types/languages; collections can overlap.
• get_data_qualitySnapshot coverage and missing metadata, unresolved loaded-authority links, and sanitized refresh status. Missing catalogue metadata is not evidence of real-world absence.
• get_snapshot_changesPage added/updated/deleted records between retained snapshots from this Omeka instance. Lists available snapshot IDs when fewer than two exist. For recent additions without history, use added_since on the search tools.
• searchRanked search across items, publications, videos, podcasts, projects and sections. Returns typed IDs, titles and citation URLs. Fetch selected records for evidence.
• fetchRead a typed search result as a cited document. Full text/transcripts are opt-in and pageable; metadata and text respect exposure policy. Unknown ID returns an error.

Questions