Skip to content
MCP server

AMIRA — Africa Multiple Research Data

Search a university research atlas of African studies items, people, papers and videos

Pricing
Open source
Platforms
CLI, API, self-hosted
Runs
Locally or Remotely
Version
1.38.1
Listing updated
2 days ago

About AMIRA — Africa Multiple Research Data

AMIRA — Africa Multiple Research Data is an open-source MCP server for education and exams. It can run locally on your machine or as a hosted remote server.

AMIRA is the research-data platform of the Africa Multiple Cluster of Excellence at the University of Bayreuth, published on a public Omeka S site. This server opens it to AI clients read-only, with 36 core tools, five research-workflow prompts and resources for citable records and bulk exports. A dated snapshot from 6 October 2026 lists 3,975 research items, 93 projects, 555 publications, 87 journals, 43 podcast episodes, 140 videos and 3,085 subject authorities.

Searches filter by subject, hierarchy-aware location, country (with aliases such as Côte d'Ivoire for Ivory Coast), contributor, project, language, year and whether media is attached. Item records include typed dates, roles with affiliation at the time, places, provenance, a IIIF manifest and generated citations in BibTeX, RIS or CSL-JSON. Every record carries an amira_url pointing to its public page so findings can be cited as links.

The server bundles a data snapshot in its .mcpb package and works offline, then optionally refreshes from the Omeka S API on startup and daily. No API key, credentials or VPN are needed.

Install

Run in a terminal

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

Add to Settings → Connectors → Add custom connector

https://data.africamultiple.uni-bayreuth.de/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "amira-mcp-server": {
      "url": "https://data.africamultiple.uni-bayreuth.de/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "amira-mcp-server": {
      "type": "http",
      "url": "https://data.africamultiple.uni-bayreuth.de/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

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

Add to your client's MCP settings (most use this shape)

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

Tools this server provides (13)

Taken from the project documentation; the running server may differ.

get_collection_overview
Counts and breakdowns across the collection with snapshot freshness.
search_research_items
Finds items by keyword, subject, location, country, project, language, year and more.
get_research_item
Full metadata for one item with media, IIIF manifest and generated citation.
search_projects
Searches projects by keyword, acronym, university, PI, member or funder.
get_project
Project detail with item breakdown and sample items.
search_persons
Searches people in either name order.
get_person
Profile with authority identifiers, roles, items and publications.
list_subjects
Subject headings ranked by item frequency.
list_locations
Places ranked by item count with coordinates and Wikidata ids.
list_collections
Collections ranked by research-item count.
list_years
Date histogram of research items by year or decade.
search_publications
Filters the bibliography by author, subject, language, type, venue and year.
get_publication
Publication detail with abstracts and linked authorities.

What it does

Item and project search
Filter research items by subject, place, country, contributor, project, language and year.
Publication full text
The bibliography is searchable by abstract and extracted open-access PDF text.
Podcasts and videos
Episodes and cluster videos are searchable by transcript.
Generated citations
BibTeX, RIS and CSL-JSON exports with a public amira_url on each record.
Offline-first data
A bundled snapshot works without setup and refreshes from the API when available.
Places and subjects
Subject headings and locations ranked by item count, with coordinates and Wikidata ids.

Good for

  • Find digitised research items about a country, place or subject
  • Look up a researcher's profile, projects and publications
  • Search the cluster bibliography for a topic in abstracts or PDFs
  • Export citations for items in BibTeX or RIS
  • Map how many items cover a place or period

Pricing

Open source

Free, read-only access to openly published data

AMIRA — Africa Multiple Research Data FAQ

Do I need credentials?

No API key, credentials or VPN are needed; it uses openly published data.

Can it change data?

No. It is read-only.

How current is the data?

The bundled snapshot is refreshed from the Omeka S API at startup and daily, with a weekly forced crawl. get_collection_overview shows what the running server holds.

Where should I start?

Call get_collection_overview first to scope the data, then drill in.

How do I cite a result?

Each record carries an amira_url to its public page, and item and publication tools can produce citations.

Is AMIRA — Africa Multiple Research Data free?

Yes. AMIRA — Africa Multiple Research Data is open source, so you can use and self-host it for free.

How do I add AMIRA — Africa Multiple Research Data to Claude Code?

Run this command in your terminal: claude mcp add --transport http amira-mcp-server https://data.africamultiple.uni-bayreuth.de/mcp

What are the best alternatives to AMIRA — Africa Multiple Research Data?

The closest alternatives to AMIRA — Africa Multiple Research Data are Agent-Native Analytics, Google Ads + Meta Ads + SEO/GEO MCP, Tapetide - Indian Stock Market MCP, World Monitor and CompanyData.

Alternatives to AMIRA — Africa Multiple Research Data

  1. Open-source analytics app where an AI agent builds charts and dashboards from your data

    • Remote
    • Open source
    • 7.7K GitHub stars
    • Analytics and data
  2. Hosted MCP connector for managing Google Ads, Meta Ads, GA4 and Search Console from chat

    • 8 tools
    • Remote
    • Freemium
    • 8.1K GitHub stars
    • Marketing and SEO
  3. Indian NSE and BSE stock market data for AI assistants through 48 MCP tools

    • 17 tools
    • Remote
    • Freemium
    • 150 GitHub stars
    • Finance and payments
  4. World Monitor

    MCP server

    Live geopolitical intelligence dashboard with an API and MCP server for agents

    • Remote
    • Freemium
    • Analytics and data
  5. CompanyData

    MCP server

    Search and enrich company records from official registers via the CompanyData API

    • 3 tools
    • Remote
    • Paid
    • 3 GitHub stars
    • Analytics and data
  6. ChartAnt

    MCP server

    Remote MCP server returning charts, maps and dashboards as hosted PNG links

    • 51 tools
    • Remote
    • Freemium
    • Design and media