Official MCP RegistryListed
AMIRA — Africa Multiple Research Data
Read-only access to AMIRA, the Africa Multiple research-data platform on Omeka S.
First seen 7 Oct 2026. Evidence as of 7 Oct 2026.
29
Tools
From an anonymous probe
1
Source listings
Each with its own history
1
Recorded changes
Since first seen
Tools
| Tool | Description | Behaviour |
|---|---|---|
| fetch | Retrieve one AMIRA record by an `id` from the search tool. Returns { id, title, text, url, metadata } — `text` concatenates the record's descriptive fields, `url` is the citable AMIRA/Omeka page, and DOI / watch / listen URLs appear in metadata when available. Large text is OPT-IN: video and podcast transcripts, and publications' extracted PDF full text, are omitted by default (metadata reports has_transcript / transcript_length and has_fulltext / fulltext_length) because either can run to tens of thousands of characters. Set the matching include_* flag to append one, and page it with the offset/max_chars pair — the window is sized to what `max_chars` leaves after the metadata header, and `*_returned_chars` is exactly what landed in `text`, so the next page starts at offset + returned_chars with no gap. | Read-only |
| find_related | Cross-entity discovery: given one entity, find what it connects to through the research items that mention it — for 'what subjects/people/places co-occur with X?' and for tracing how a theme spans projects. Returns the matched-item count plus ranked related projects, research sections, subjects, people, countries and formats, sample items, and the seed's own `amira_url`. Subject and person seeds also pivot into the cluster bibliography (related_publications). How the value was matched is echoed in the response `matching` field — note `matched_items` counts ITEMS, so it differs from list_subjects, which counts distinct headings. | Read-only |
| get_collection_overview | START HERE to scope the collection before drilling in with the search/list tools: counts across every corpus (projects, research items, people, institutions, groups, publications, podcasts, videos, and how many carry full text or transcripts), breakdowns of items by university, research section, resource type and language, the content date range, and the data snapshot's freshness. Takes no arguments. | Read-only |
| get_institution | Detail for one institution (or group) by `name` (case-insensitive). Returns the projects it funds/hosts, the research items crediting it (slim refs, capped at 50, total reported), people affiliated with it, coordinates when known, and a citable `amira_url`. Returns { error } if the name is not in the organisation authority list. | Read-only |
| get_person | Aggregate everything the collection knows about one person: affiliations, projects led (PI) and joined (member), research items contributed with the person's role (capped at 50, the total reported), publications authored or edited, and a citable `amira_url`. The canonical 'Surname, Forename' spelling is echoed back as `name`. Works even for names absent from the authority list — empty lists mean the name appears nowhere. | Read-only |
| get_podcast | Full detail for one podcast episode: series, episode number, date and `date_status` (published/scheduled/unknown), abstract, people with roles, the episode URL and the citable `amira_url`. The transcript is OMITTED by default (only has_transcript + transcript_length are shown) — pass include_transcript=true and page a long one. Returns { error } if the id is unknown. | Read-only |
| get_project | Full detail for one project by Omeka `id` (preferred; the numeric o:id in `amira_url`). Legacy project-key values are still accepted for compatibility. Returns name, university, research sections, principal investigators, members, description, start/end dates, funding institutions, project website, item_count, a breakdown of its items by resource type, its top subjects, and a citable `amira_url`. Returns { error } if the id is unknown. | Read-only |
| get_publication | Publication metadata, linked authors/editors/publisher/venue, conference details, page extent, access statements, thesis advisers, supplementary links, and a citation export (BibTeX default). Full text is omitted unless include_fulltext=true; page long texts. Cite amira_url; DOI/repository url is an additional link. Unknown id returns { error }. | Read-only |
| get_research_item | Full metadata for one research item: typed content dates, contributors with roles, subjects, places with their region/country chain, project/section/university, collections, descriptive text, formats and physical notes, sponsors, provenance, rights, identifiers, related items, languages, a media thumbnail, and the citable `amira_url`. Also returns a ready-to-use `generated_citation` string plus a `bibtex` entry built from those fields (items rarely carry a `citation` of their own) — `citation_format` swaps BibTeX for RIS or CSL-JSON. Long text fields are truncated at 25,000 characters. Returns { error } if the id is unknown. | Read-only |
| get_research_section | Full detail for one research section by `name` (case-insensitive, e.g. 'Mobilities'). Returns the funding_phase (AM 1.0 / 2019–2025 or AM 2.0 / 2026–2032) and its date range, the full description, principal investigators, members, spokesperson, the section's page on the cluster website, the projects belonging to it (with item counts), the total item count, and a citable `amira_url`. Returns a structured { error } (with the valid names in `available_values`) if the name is unknown. | Read-only |
| get_video | Full detail for one YouTube video: upload date and `date_status`, abstract, playlists, speakers, languages, the watch URL and the citable `amira_url`. The transcript is OMITTED by default (transcripts are large; only has_transcript + transcript_length are shown) — pass include_transcript=true and page a long one. Returns { error } if the id is unknown. | Read-only |
| list_categories | List the distinct values of one categorical facet across research items, ranked by item count (languages also carry their ISO `code`). Feed values back into the matching search_research_items filter: `genre` for formats, `language`, `resource_type`. | Read-only |
| list_cluster_partners | List Africa Multiple partner institutions by Omeka partner-category authority: Africa Multiple Research Centres, Privileged partner, Cooperation partners, and Global partner Centres of African Studies. Optional `category` accepts amrc, privileged, cooperation, global, or a category label. Results include institution coordinates, Wikidata URI, category authority Omeka ids, and citable `amira_url` links. | Read-only |
| list_collections | List the collections (Omeka item sets) research items belong to — per-project collections, external archives (e.g. ILAM) and curated sets — ranked by item count, each with its browsable page. Feed a title or id into the `collection` filter of search_research_items. | Read-only |
| list_groups | List research groups (organisation authority records typed 'Group'). Optional `keyword` filters by name; `limit` (default 50, max 200) and `offset` paginate. Each result has name, contributed_item_count (items crediting the group) and a citable `amira_url`. Use get_institution with the group's name for its items. | Read-only |
| list_institutions | List institutions in the authority list. Optional `keyword` filters by name; `limit` (default 50, max 200) and `offset` paginate. Each result has name, project_count (projects it funds/hosts), coordinates when reconciled, and a citable `amira_url`. Use get_institution for the affiliated projects and contributed items. Research groups are a separate list — see list_groups. | Read-only |
| list_journals | List the journals the cluster publishes in (the Journal venue authority), ranked by how many publications appeared in each, with ISSN, country of publication and website. Feed a title into the `venue` filter of search_publications to retrieve its articles. | Read-only |
| list_locations | List every place the research items come from, ranked by item count, with coordinates where known. Countries and cities sit in ONE flat list (there is no level to choose) and the hierarchy is rolled up, so an item from Lagos counts toward both Lagos and Nigeria and both appear. Feed a name straight into the `location` filter of search_research_items. | Read-only |
| list_publication_facets | Count publications by type, year, language, subject, author/editor or venue across the complete filtered bibliography. Each publication counts once per value; missing_values counts records without this facet. Ranked by count, paginated. Use values in search_publications filters. | Read-only |
| list_research_sections | List the cluster's research sections (its top-level thematic structure), with funding phase, PIs, member/project/item counts and a citable `amira_url`. Sections split by funding phase: AM 1.0 / 2019–2025 (Affiliations, Arts & Aesthetics, Knowledges, Learning, Mobilities, Moralities) and AM 2.0 / 2026–2032 (Accumulation, Digitalities, Ecologies, In/securities, Re:membering, Translating), plus a synthetic 'External' grouping. The AM 2.0 sections are newly seeded and currently hold ~0 projects/items. Takes no arguments; use get_research_section for one section's full description and project list. | Read-only |
| list_subjects | List the subject headings used across research items, ranked by how many items carry each, with each subject's own authority page. Subjects absorb the former free-form tags — there is no separate tag facet. Feed a value into the `subject` filter of search_research_items to retrieve the items. | Read-only |
| list_years | Date histogram of the research items: how many fall in each year (or decade) of their content dates — for coverage-over-time and most-covered-year questions. The response also reports dated_items, undated_items and the observed year_range. An item whose content date is a RANGE counts toward every year it spans, so bucket counts can sum to more than dated_items — the same semantics as the year_from/year_to filter of search_research_items, into which a year can be fed back. Years have no authority page, so results carry no amira_url. | Read-only |
| search | Search the Africa Multiple (AMIRA) research collection, ranked by relevance. Covers research items (digitised artefacts), the cluster bibliography (reaching INTO the extracted full text of open-access publications), podcasts and YouTube videos (reaching INTO their transcripts), and the cluster's projects and research sections. Matching is accent-insensitive. Returns { results: [{ id, title, url }] }, where `url` is the citable AMIRA/Omeka record page; pass an `id` to the fetch tool for the full record. (The OpenAI/ChatGPT-compatible entry point; richer filtered tools — search_research_items, find_related, list_* — are also available.) | Read-only |
| search_persons | Search the people authority list (researchers and contributors). Names are stored 'Surname, Forename' and matching is order-independent and accent-insensitive, so 'Oliver Baumann', 'Baumann, Oliver' and 'Baumann' all find the same person. Use get_person for a full profile. | Read-only |
| search_podcasts | Search the cluster's podcast episodes (e.g. the 'Cluster Conversations' series; ~43 episodes, all with AI-generated transcripts). Keyword search reaches INTO the transcripts — a transcript-only hit is flagged `matched_in: 'transcript'` with a `transcript_snippet` around the match. Filters are optional and AND-combined. Use get_podcast for one episode's detail and the transcript itself. | Read-only |
| search_projects | Search the cluster's research projects across AMIRA's partner/source metadata labels plus external collections. Every registered project is searchable; `item_count` shows how many carry digitised items (a subset do). Filters are optional and AND-combined; omit all to list every project. Use get_project for full detail. | Read-only |
| search_publications | Search the ERef/EPub cluster bibliography. Filters are AND-combined; newest first. Keyword reaches extracted PDF text, with matched_in='fulltext' and a snippet for text-only hits. Use list_publication_facets for types, years, languages, subjects, contributors and venues; get_publication for detail. Set citation_format to export complete entries (no abstracts/full text); follow next_offset until has_more=false. Cite amira_url; DOI/repository url is an additional link. | Read-only |
| search_research_items | The main discovery tool: search the ~4,000 research items (digitised artefacts — images, texts, audio, video) across all Africa Multiple project collections, including for 'items about subject X' and 'items from location Y'. Filters are optional and AND-combined; omit all to browse. Use get_research_item for one item's full detail. When a filter combination matches nothing, the response adds `suggestions` naming which single filter to drop and how many items that would surface. | Read-only |
| search_videos | Search the Africa Multiple YouTube channel videos catalogued in the collection (~140 lectures, interviews and events; most carry transcripts). Keyword search reaches INTO the transcripts — the main full-text search over cluster talks — and flags such a hit as `matched_in: 'transcript'` with a `transcript_snippet`. Filters are optional and AND-combined. Use get_video for one video's detail and the transcript itself. | Read-only |
Change history
- Listed (registry)
| Source | Listing | First seen | Last seen | Versions |
|---|---|---|---|---|
| Official MCP Registry | io.github.AM-Digital-Research-Environment/amira-mcp-server | 7 Oct 2026 | 7 Oct 2026 | 1 |