Agents Index

AMIRA — Africa Multiple Research Data

Online

Read-only access to AMIRA, the Africa Multiple research-data platform on Omeka S.

Visit publisherConnectJSON

What it can do: 40 tools

  • get_collection_overview read-onlyStart here: corpus counts, text coverage, breakdowns, dates, snapshot freshness and refresh status.
  • search_research_items read-onlySearch 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_item read-onlyResearch-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_projects read-onlySearch project names, descriptions and membership. Returns cited summaries and item counts; use get_project for detail.
  • get_project read-onlyProject description, team, sections, funders, item counts by type, top subjects and ten sample research items, with citation links.
  • list_research_sections read-onlyCluster research sections, funding phases, project/item counts and citation links. Includes the external-collection grouping.
  • get_research_section read-onlyOne research section's description, team and projects, each with its research-item count.
  • search_persons read-onlyFind canonical person authority records. Names accept either order and ignore accents. Use resolve_entity to disambiguate homonyms.
  • get_person read-onlyPerson affiliations, identifiers, project and section roles, credited items, publications, podcasts, videos, Cluster Chronicles works and collaborators. Lists cap at 50 with totals. Use id to disambiguate.
  • list_institutions read-onlyBrowse institution authorities (and untyped organisations, marked kind) by name or acronym (e.g. 'UJKZ'), with project counts and citation links.
  • get_institution read-onlyInstitution or group profile: identifiers, members, funded projects and credited items, with citation links.
  • list_cluster_partners read-onlyCluster partner institutions grouped by catalogue category, with citation links.
  • list_groups read-onlyBrowse group authorities by name, mostly performing ensembles credited on research items, with item counts and citation links.
  • list_subjects read-onlySubject headings (LCSH or free tags) ranked by distinct research-item count. Feed a heading into search_research_items.subject.
  • list_locations read-onlyResearch places with coordinates and ancestor rollups. Two tiers: level "country" or "place" (city, region or site); one item counts under both. Feed a name into search_research_items.location.
  • list_collections read-onlyResearch collections, one per project, ranked by research-item count and cited by the project page. Feed an id or code into search_research_items.collection.
  • list_categories read-onlyRanked formats, languages or resource types used by research items. Feed values into the corresponding search filters.
  • list_years read-onlyResearch-item year/decade histogram with dated and undated counts. A date range counts in each spanned bucket. dated_items and year_range follow from/to. Supports item filters and paging.
  • search_publications read-onlyAND-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_publication read-onlyPublication metadata and citation export (BibTeX default). Full text is opt-in and paginated. Cite amira_url; DOI/repository links are additional sources.
  • list_publication_facets read-onlyRanked facets for the entire filtered bibliography before pagination. Uses the same selection rules as search_publications.
  • list_journals read-onlyPublication venues ranked by linked bibliography records, with ISSN and catalogue links.
  • find_related read-onlySubjects, people, places and projects connected through shared records. Per-corpus counts deduplicate each record; subject/person seeds also include publications, subject/place/person seeds Cluster Chronicles works. Retu
  • search_podcasts read-onlySearch podcast metadata and transcripts. Text-only hits include snippets; full transcripts require get_podcast with opt-in.
  • get_podcast read-onlyPodcast detail, duration, audio file and citation link; says which model generated the transcript. Transcript is opt-in, bounded and pageable.
  • search_videos read-onlySearch video metadata and transcripts. Text-only hits include snippets; full transcripts require get_video with opt-in.
  • get_video read-onlyVideo detail, thumbnail and citation link; says how the transcript was produced when recorded. Transcript is opt-in, bounded and pageable.
  • search_chronicles read-onlySearch Cluster Chronicles works (writer-in-residence essays, poems, photos, events) by chronicler, form, year, subject, place or keyword. Text-only hits include snippets.
  • get_chronicle read-onlyOne Cluster Chronicles work: chroniclers and roles, people depicted, subjects, places, related works and recordings, images, links. Abstracts are AI-written (says which model). Text opt-in and pageable.
  • resolve_entity read-onlyResolve 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_graph read-onlyOne-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_passages read-onlyFind accent-insensitive passages of one literal phrase (quotes optional; words are not matched separately) in selected publication/video/podcast/chronicle IDs. Original UTF-16 offsets, bounded context, citations. Require
  • compare_collections read-onlyCompare 2–4 projects or collections (id or code from list_collections) with identical research-item filters. Reports denominators, missingness, dates and top types/languages.
  • get_data_quality read-onlySnapshot coverage and missing metadata, unresolved loaded-authority links, semantic-neighbour coverage and sanitized refresh status. Missing catalogue metadata is not evidence of real-world absence.
  • get_snapshot_changes read-onlyPage 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.
  • get_fulltext_map read-onlyILAM's journal African Music by its private full text, from public derived counts: AI-labelled content groups, countries named, word rates per year. Never returns text.
  • get_similar_items read-onlyRecords whose catalogue descriptions read most alike (EmbeddingGemma 2 vectors), across research items, publications, videos, podcasts, projects and sections. Each says what else it shares (subjects, places, people, proj
  • get_semantic_map read-onlyThe collection as unnamed groups of records close in meaning (k-means over EmbeddingGemma 2 vectors): size, type mix, top subjects, countries and projects, records nearest the centre. `group` lists one; `id` finds a reco
  • search read-onlyRanked search across items, publications, videos, podcasts, projects and sections. Returns typed IDs, titles and citation URLs. Fetch selected records for evidence.
  • fetch read-onlyRead 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.

Connect it

Claude Code
claude mcp add --transport http amira-africa-multiple-research-data https://data.africamultiple.uni-bayreuth.de/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://data.africamultiple.uni-bayreuth.de/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "amira-africa-multiple-research-data": {
      "url": "https://data.africamultiple.uni-bayreuth.de/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "amira-africa-multiple-research-data": {
      "type": "http",
      "url": "https://data.africamultiple.uni-bayreuth.de/mcp"
    }
  }
}

Questions

What does AMIRA — Africa Multiple Research Data do?

Read-only access to AMIRA, the Africa Multiple research-data platform on Omeka S. It exposes 40 tools to AI assistants.

What tools does AMIRA — Africa Multiple Research Data provide?

40 tools, including get_collection_overview, search_research_items, get_research_item, search_projects, get_project, list_research_sections, get_research_section, search_persons, get_person, list_institutions, get_institution, list_cluster_partners….

How do I connect AMIRA — Africa Multiple Research Data to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://data.africamultiple.uni-bayreuth.de/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does AMIRA — Africa Multiple Research Data require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is AMIRA — Africa Multiple Research Data online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes AMIRA — Africa Multiple Research Data?

@AM-Digital-Research-Environment on GitHub. The official MCP Registry verified that the publisher controls this GitHub account before accepting the listing.

Similar in Research & Knowledge