# AMIRA — Africa Multiple Research Data

- Registry name: `io.github.AM-Digital-Research-Environment/amira-mcp-server` · version 1.25.0
- Categories (automatic, keyword rules): Research & knowledge, Search & data
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): completions, extensions, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.AM-Digital-Research-Environment%2Famira-mcp-server
- Server page: https://mcpstation.net/s/io.github.AM-Digital-Research-Environment--amira-mcp-server.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://data.africamultiple.uni-bayreuth.de/mcp`

## Tools (as reported by the server, not verified)

- `get\_collection\_overview`: Start here: corpus counts, text coverage, breakdowns, dates, snapshot freshness and refresh status.
- `search\_research\_items`: 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.
- `get\_research\_item`: 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.
- `search\_projects`: Search project names, descriptions and membership. Returns cited summaries and item counts; use get\_project for detail.
- `get\_project`: Project description, team, sections, funders, item counts by type, top subjects and ten sample research items, with citation links.
- `list\_research\_sections`: Cluster research sections, funding phases, project/item counts and citation links. Includes the external-collection grouping.
- `get\_research\_section`: One research section's description, team and projects, each with its research-item count.
- `search\_persons`: Find canonical person authority records. Names accept either order and ignore accents. Use resolve\_entity to disambiguate homonyms.
- `get\_person`: Person affiliations, identifiers, project and section roles, credited items, publications, podcasts, videos and collaborators. Lists cap at 50 with totals. Use id to disambiguate.
- `list\_institutions`: Browse institution authorities by name or acronym \(e.g. 'UJKZ'\), with project counts and citation links.
- `get\_institution`: Institution or group profile: identifiers, members, funded projects and credited items, with citation links.
- `list\_cluster\_partners`: Cluster partner institutions grouped by catalogue category, with citation links.
- `list\_groups`: Browse research groups and associations by name, with citation links.
- `list\_subjects`: Subject headings \(LCSH or free tags\) ranked by distinct research-item count. Feed a heading into search\_research\_items.subject.
- `list\_locations`: Research places with coordinates and ancestor rollups. One item can count under both city and country. Feed a name into search\_research\_items.location.
- `list\_collections`: Omeka item sets ranked by research-item count, with catalogue links. Feed an ID into search\_research\_items.collection.
- `list\_categories`: Ranked formats, languages or resource types used by research items. Feed values into the corresponding search filters.
- `list\_years`: Research-item year/decade histogram with dated and undated counts. A date range counts in each spanned bucket. Supports shared item filters and pagination.
- `search\_publications`: 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.
- `get\_publication`: Publication 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`: Ranked facets for the entire filtered bibliography before pagination. Uses the same selection rules as search\_publications.
- `list\_journals`: Publication venues ranked by linked bibliography records, with ISSN and catalogue links.
- `find\_related`: Subjects, 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\_podcasts`: Search podcast metadata and transcripts. Text-only hits include snippets; full transcripts require get\_podcast with opt-in.
- `get\_podcast`: Podcast detail, duration, audio file and citation link; says which model generated the transcript. Transcript is opt-in, bounded and pageable.
- `search\_videos`: Search video metadata and transcripts. Text-only hits include snippets; full transcripts require get\_video with opt-in.
- `get\_video`: Video detail, thumbnail and citation link; says how the transcript was produced when recorded. Transcript is opt-in, bounded and pageable.
- `resolve\_entity`: 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.
- `get\_entity\_graph`: 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.
- `get\_text\_passages`: Find 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\_collections`: Compare 2–4 projects or item sets with identical research-item filters. Reports denominators, missingness, dates and top types/languages; collections can overlap.
- `get\_data\_quality`: Snapshot coverage and missing metadata, unresolved loaded-authority links, and sanitized refresh status. Missing catalogue metadata is not evidence of real-world absence.
- `get\_snapshot\_changes`: 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.
- `search`: Ranked search across items, publications, videos, podcasts, projects and sections. Returns typed IDs, titles and citation URLs. Fetch selected records for evidence.
- `fetch`: 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.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html