mcpField
M
mcp-research-topic-institutions-authors

mcp-research-topic-institutions-authors

Local
github.com/mambalabsdevSearch0Updated 2d ago

About mcp-research-topic-institutions-authors

An Apify-backed MCP server that ranks institutions and authors by their works on a research topic, using OpenAlex data. Researchers can search by keywords or OpenAlex topic IDs and retrieve publication metrics and recent papers.

Key features

  1. 01Search keywords or OpenAlex topic IDs
  2. 02Rank institutions and authors by works
  3. 03Filter by years, countries, and institution types
  4. 04Return publication metrics and recent papers

Use cases

  1. 01Identify institutions publishing on a research topic
  2. 02Find leading authors and their recent papers
  3. 03Compare topic-related research across countries

MCP support

Exposes the `find_research_topic_institutions_authors` tool to MCP clients. It starts the Apify actor, waits for completion, and returns dataset rows.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"com-mambabuilt-mcp-research-topic-institutions-authors": {
"command": "npx",
"args": [
"-y",
"@mambalabsdev/mcp-research-topic-institutions-authors"
],
"env": {
"APIFY_TOKEN": "<APIFY_TOKEN>"
}
}
}
}
Run commandnpx -y @mambalabsdev/mcp-research-topic-institutions-authors
Environment variables to set
APIFY_TOKENSecretApify API token from https://console.apify.com/account/integrations

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@mambalabsdev/mcp-research-topic-institutions-authors1.0.2

Tools

1

Saved tool list · updated 2d ago

ParameterTypeRequiredDescription
topicsarrayNoKeywords such as perovskite solar cells, or OpenAlex topic IDs such as T10247, up to 20. Each one gets its own ranked rows.
to_yearnumberNoCount works published up to this year. Default no end.
countriesarrayNoTwo letter codes such as US or DE. Institution rows must be in one of these. Author rows come from works with an institution in one of these, and the author may be elsewhere.
from_yearnumberNoCount works published from this year. Default 5 years before the current year.
row_typesarrayNoinstitutions, authors, or both. Default both.
max_authorsnumberNoAuthor rows per topic, up to 200. Default 25.
search_scopeenumNotitle_abstract (default): a keyword must be in the title or abstract. fulltext: also the full text where OpenAlex holds it, which matches more and less precisely. Ignored for topic IDs.title_abstract | fulltext
recent_papersnumberNoNewest papers on the topic to add to each row, 0 to 10. Default 3. 0 skips them and uses far less of the OpenAlex budget.
max_charge_usdstringNoOptional. The run stops before a charge that would pass this amount. Summary rows are always returned.
max_institutionsnumberNoInstitution rows per topic, up to 200. Default 25.
openalex_api_keystringNoOptional. Your own free key from openalex.org/settings/api, with its own 1 USD a day of OpenAlex usage. Without one, the run shares a 0.10 USD daily budget with everyone on its address and keyword search can be limited. Never stored or logged.
institution_typesarrayNoAny of education, healthcare, company, archive, nonprofit, government, facility, funder, other. Institution rows must be one of these. Author rows come from works with such an institution.

Details

From the project README

Research Topic Institutions and Authors MCP Server

npm version license

An MCP server for the Mamba Labs Research Topic Institutions and Authors actor on Apify. Turn a research topic into ranked institutions and authors from OpenAlex.

What's Inside

What it does

Give a research topic as a keyword or OpenAlex topic ID. The actor groups matching OpenAlex works and returns one row per institution or author, ranked by works on the topic, with ROR, ORCID, total works, citations, h-index, and newest papers on the topic. It returns only what OpenAlex publishes, and no email or phone. A free OpenAlex key from the buyer is optional and gives that buyer a larger daily budget.

All of the work runs on Apify. This package is a thin client that starts the actor run, waits for it, and hands back the dataset rows.

Quick start

You need Node.js 18 or newer and an Apify account with an API token.

Add this to your Claude Desktop config (claude_desktop_config.json), Cursor, or any MCP client:

{
  "mcpServers": {
    "mamba-research-topic-institutions-authors": {
      "command": "npx",
      "args": [
        "-y",
        "@mambalabsdev/mcp-research-topic-institutions-authors"
      ],
      "env": {
        "APIFY_TOKEN": "your-apify-token"
      }
    }
  }
}

Restart the client. The find_research_topic_institutions_authors tool appears.

Prerequisites

Example prompts

  • "Which institutions publish the most on perovskite solar cells?"
  • "Find the top authors on CRISPR base editing since 2022, with their newest papers."
  • "List companies publishing on solid state batteries in Germany."

Tool

find_research_topic_institutions_authors. One tool. Example arguments:

{
  "topics": [
    "perovskite solar cells"
  ],
  "max_institutions": 5,
  "max_authors": 5,
  "recent_papers": 2
}

Inputs

Every buyer facing input of the actor. Omitted inputs take the actor's own defaults.

InputTypeRequiredDescription
topicsarraynoKeywords such as perovskite solar cells, or OpenAlex topic IDs such as T10247, up to 20. Each one gets its own ranked rows.
row_typesarraynoinstitutions, authors, or both. Default both.
max_institutionsnumbernoInstitution rows per topic, up to 200. Default 25.
max_authorsnumbernoAuthor rows per topic, up to 200. Default 25.
recent_papersnumbernoNewest papers on the topic to add to each row, 0 to 10. Default 3. 0 skips them and uses far less of the OpenAlex budget.
from_yearnumbernoCount works published from this year. Default 5 years before the current year.
to_yearnumbernoCount works published up to this year. Default no end.
countriesarraynoTwo letter codes such as US or DE. Institution rows must be in one of these. Author rows come from works with an institution in one of these, and the author may be elsewhere.
institution_typesarraynoAny of education, healthcare, company, archive, nonprofit, government, facility, funder, other. Institution rows must be one of these. Author rows come from works with such an institution.
search_scopestringnotitle_abstract (default): a keyword must be in the title or abstract. fulltext: also the full text where OpenAlex holds it, which matches more and less precisely. Ignored for topic IDs.
openalex_api_keystringnoOptional. Your own free key from openalex.org/settings/api, with its own 1 USD a day of OpenAlex usage. Without one, the run shares a 0.10 USD daily budget with everyone on its address and keyword search can be limited. Never stored or logged.
max_charge_usdstringnoOptional. The run stops before a charge that would pass this amount. Summary rows are always returned.

Pricing

Pay per event on Apify, billed to your Apify account. Prices in USD.

EventFree planBronzeSilverGold
entity-row, one institution or author row$0.006$0.0057$0.0054$0.0051
apify-actor-start, per run start$0.003$0.003$0.003$0.003

Topic summaries, refused or failed topics, and refused input are free. Mamba Labs pays the platform costs of the run. Mamba Labs pays the platform costs of the run, Apify proxy traffic included.

Full actor documentation

apify.com/mambalabs/research-topic-institutions-authors

License

MIT. See LICENSE.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.