AMIRA — Africa Multiple Research Data
Server Details
Read-only access to AMIRA, the Africa Multiple research-data platform on Omeka S.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- AM-Digital-Research-Environment/amira-mcp-server
- GitHub Stars
- 2
- Server Listing
- AMIRA MCP Server
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 40 tools
Most tools are resource-specific and clearly named, but there are overlapping clusters: generic `fetch` versus typed `get_*` tools, generic `search` versus resource-specific searches, and `find_related` versus `get_entity_graph`. Descriptions help distinguish intent, but an agent must read carefully to choose correctly.
All tool names use snake_case and follow a predictable verb_noun pattern such as `get_publication`, `search_podcasts`, and `list_institutions`. The few generic names (`fetch`, `search`) are minor and still fit the overall convention.
The 40 tools reflect a genuinely broad multi-resource research catalogue, with search/get/list operations across many entity types, so the surface is not arbitrary. However, it is heavy for a single MCP server and increases selection burden compared with a tighter, more scoped interface.
Coverage is extensive for a read-only research-data domain: search, retrieval, entity graphs, semantic maps, text passages, snapshots, quality checks, and citation exports are all present. Minor gaps remain around detailed getters for some browsable entities such as groups, journals, locations, and categories.
Available Tools
40 toolscompare_collectionsCompare project collectionsARead-onlyIdempotentInspect
Compare 2–4 projects or collections (id or code from list_collections) with identical research-item filters. Reports denominators, missingness, dates and top types/languages.
Inputs: cohorts (required), filters. Returns: cohorts, snapshot_id, overlap_note
fetchFetch one AMIRA recordARead-onlyIdempotentInspect
Read 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.
Inputs: id (required), max_chars, fulltext_offset, include_fulltext, +4 more. Returns: id, url, text, title, +1 more
get_chronicleGet Cluster Chronicles workARead-onlyIdempotentInspect
One 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.
Inputs: id (required), text_offset, include_text, text_max_chars.
get_collection_overviewAfrica Multiple collection overviewARead-onlyIdempotentInspect
Start here: corpus counts, text coverage, breakdowns, dates, snapshot freshness and refresh status.
Inputs: no named parameters. Returns: counts, refresh, site_url, universities, +10 more
get_data_qualityInspect data coverageBRead-onlyIdempotentInspect
Snapshot 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.
Inputs: no named parameters. Returns: counts, missing, refresh, fetched_at, +5 more
get_entity_graphExplore an entity graphARead-onlyIdempotentInspect
One-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 snapshot_id across pages.
Inputs: seed (required), limit, types, offset, +4 more. Returns: seed, count, edges, nodes, +15 more
get_fulltext_mapILAM full-text mapBRead-onlyIdempotentInspect
ILAM'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.
Inputs: group, words, year_to, year_from.
get_institutionGet institution detailBRead-onlyIdempotentInspect
Institution or group profile: identifiers, members, funded projects and credited items, with citation links.
Inputs: id, name.
get_personGet person profileBRead-onlyIdempotentInspect
Person 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.
Inputs: id, name.
get_podcastGet podcast episode detailARead-onlyIdempotentInspect
Podcast detail, duration, audio file and citation link; says which model generated the transcript. Transcript is opt-in, bounded and pageable.
Inputs: id (required), include_similar, transcript_offset, include_transcript, +1 more.
get_projectGet project detailARead-onlyIdempotentInspect
Project description, team, sections, funders, item counts by type, top subjects and ten sample research items, with citation links.
Inputs: id (required), include_similar.
get_publicationGet publication detailARead-onlyIdempotentInspect
Publication metadata and citation export (BibTeX default). Full text is opt-in and paginated. Cite amira_url; DOI/repository links are additional sources.
Inputs: id (required), citation_format, fulltext_offset, include_similar, +2 more.
get_research_itemGet research item detailARead-onlyIdempotentInspect
Research-item metadata, linked entities, rights, media files, IIIF manifest and a generated citation (BibTeX/RIS/CSL-JSON). Long fields cap at 25,000 characters.
Inputs: id (required), citation_format, include_similar.
get_research_sectionGet research section detailBRead-onlyIdempotentInspect
One research section's description, team and projects, each with its research-item count.
Inputs: id, name.
get_semantic_mapSemantic map of the collectionARead-onlyIdempotentInspect
The 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 record's group.
Inputs: id, group, limit, types, +1 more.
get_similar_itemsFind similar recordsARead-onlyIdempotentInspect
Records 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, project) or wording_only.
Inputs: id (required), limit, types.
get_snapshot_changesCompare retained snapshotsARead-onlyIdempotentInspect
Page 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.
Inputs: limit, to_id, corpus, offset, +1 more. Returns: hint, count, to_id, offset, +11 more
get_text_passagesFind cited text passagesARead-onlyIdempotentInspect
Find 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. Requires full text exposure.
Inputs: ids (required), keyword (required), limit, offset, +1 more. Returns: count, offset, results, has_more, +9 more
get_videoGet YouTube video detailBRead-onlyIdempotentInspect
Video detail, thumbnail and citation link; says how the transcript was produced when recorded. Transcript is opt-in, bounded and pageable.
Inputs: id (required), include_similar, transcript_offset, include_transcript, +1 more.
list_categoriesList a category facetARead-onlyIdempotentInspect
Ranked formats, languages or resource types used by research items. Feed values into the corresponding search filters.
Inputs: category (required), limit, offset, keyword.
list_cluster_partnersList cluster partner institutionsBRead-onlyIdempotentInspect
Cluster partner institutions grouped by catalogue category, with citation links.
Inputs: category.
list_collectionsList collectionsBRead-onlyIdempotentInspect
Research 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.
Inputs: limit, offset, keyword.
list_groupsList groupsARead-onlyIdempotentInspect
Browse group authorities by name, mostly performing ensembles credited on research items, with item counts and citation links.
Inputs: limit, offset, keyword.
list_institutionsList institutionsARead-onlyIdempotentInspect
Browse institution authorities (and untyped organisations, marked kind) by name or acronym (e.g. 'UJKZ'), with project counts and citation links.
Inputs: limit, offset, keyword.
list_journalsList journalsCRead-onlyIdempotentInspect
Publication venues ranked by linked bibliography records, with ISSN and catalogue links.
Inputs: limit, offset, keyword.
list_locationsList locationsBRead-onlyIdempotentInspect
Research 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.
Inputs: bbox, near, limit, offset, +3 more.
list_publication_facetsPublication facetsARead-onlyIdempotentInspect
Ranked facets for the entire filtered bibliography before pagination. Uses the same selection rules as search_publications.
Inputs: facet (required), type, limit, venue, +9 more. Returns: count, facet, offset, filters, +9 more
list_research_sectionsList research sectionsBRead-onlyIdempotentInspect
Cluster research sections, funding phases, project/item counts and citation links. Includes the external-collection grouping.
Inputs: no named parameters.
list_subjectsList subjectsARead-onlyIdempotentInspect
Subject headings (LCSH or free tags) ranked by distinct research-item count. Feed a heading into search_research_items.subject.
Inputs: limit, offset, keyword, vocabulary.
list_yearsList yearsARead-onlyIdempotentInspect
Research-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.
Inputs: to, from, sort, limit, +3 more. Returns: sort, count, bucket, offset, +8 more
resolve_entityResolve an entityARead-onlyIdempotentInspect
Resolve 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.
Inputs: query (required), type, limit, offset. Returns: hint, count, offset, results, +9 more
searchSearch the AMIRA collectionARead-onlyIdempotentInspect
Ranked search across items, publications, videos, podcasts, projects and sections. Returns typed IDs, titles and citation URLs. Fetch selected records for evidence.
Inputs: query (required), limit, types. Returns: results, effective_limit, requested_limit
search_chroniclesSearch Cluster ChroniclesARead-onlyIdempotentInspect
Search Cluster Chronicles works (writer-in-residence essays, poems, photos, events) by chronicler, form, year, subject, place or keyword. Text-only hits include snippets.
Inputs: form, limit, place, offset, +6 more.
search_personsSearch peopleARead-onlyIdempotentInspect
Find canonical person authority records. Names accept either order and ignore accents. Use resolve_entity to disambiguate homonyms.
Inputs: limit, offset, keyword, affiliation.
search_podcastsSearch podcastsARead-onlyIdempotentInspect
Search podcast metadata and transcripts. Text-only hits include snippets; full transcripts require get_podcast with opt-in.
Inputs: limit, offset, person, series, +4 more.
search_projectsSearch research projectsARead-onlyIdempotentInspect
Search project names, descriptions and membership. Returns cited summaries and item counts; use get_project for detail.
Inputs: limit, member, offset, keyword, +4 more.
search_publicationsSearch publicationsARead-onlyIdempotentInspect
AND-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.
Inputs: type, limit, venue, author, +10 more.
search_research_itemsSearch research itemsARead-onlyIdempotentInspect
Search 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.
Inputs: genre, limit, export, offset, +18 more.
search_videosSearch YouTube videosARead-onlyIdempotentInspect
Search video metadata and transcripts. Text-only hits include snippets; full transcripts require get_video with opt-in.
Inputs: limit, offset, keyword, speaker, +4 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Read-only access to the Islam West Africa Collection via Hugging Face datasets.
Read-only access to S. Araba Lawson's Afromorphism essays, glossary, books, and site.
Public Caribbean & diaspora cultural data: Observatory facts, territories, events.
Read-only search and retrieval of published books, articles and authors, with public catalog links.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables agents to find, read, and cite digitized primary sources published via IIIF — searching several institutions' catalogues, resolving item pages to manifests, pulling page images or regions for vision models, and generating citations with rights and provenance. Runs read-only over stateless Streamable HTTP with no login.AGPL 3.0
- AlicenseNot gradedqualityBmaintenanceA read-only MCP server for the Islam West Africa Collection (IWAC) digital archive, providing 37 tools to search and analyze newspaper articles, publications, references, and more.2MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to search and retrieve items from an Omeka S collection through the Omeka REST API, returning readable metadata and public item page links.MIT
- AlicenseAqualityBmaintenanceEnables researchers to search, count, cross-tabulate, and trace the provenance of roughly 64,000 objects in the SKKG digital collection, and to inspect and view their images along with licence and copyright information. Natural-language queries are translated into German vocabulary searches over a local read-only snapshot, with no load on SKKG's servers.12MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.