ScholarFetch

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Multi-engine scholarly research server for search, traversal, full text, and reading lists.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "ScholarFetch": {
      "url": "https://laibniz-scholarfetch-web.hf.space/mcp/",
      "transport": "streamable-http"
    }
  }
}

Measured tools (12)

• scholarfetch_search

  Start a research traversal from keywords, a DOI, or a person name. Returns deduplicated paper records that you can inspect, save, expand through references, or use as seeds for author exploration. If you pass `engines`, use a comma-separated subset of: elsevier, openalex, crossref, arxiv, europepmc, springer, semanticscholar.

  Parameters:

  • query (required) — string
  • limit — integer
  • engines — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• scholarfetch_doi_lookup

  Enrich one known DOI with metadata, reading links, and full-text availability signals. If you pass `engines`, use a comma-separated subset of: elsevier, openalex, crossref, arxiv, europepmc, springer, semanticscholar.

  Parameters:

  • doi (required) — string
  • engines — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• scholarfetch_author_candidates

  Disambiguate a human author name into ranked identity candidates. Use this before `scholarfetch_author_papers` when the name is ambiguous and you need a stable `candidate_index`. If you pass `engines`, it must include `openalex`.

  Parameters:

  • name (required) — string
  • limit — integer
  • engines — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• scholarfetch_author_papers

  Expand one author into a deduplicated paper list. This is the main author->paper traversal tool and supports research filters. Use `author_id` when you already know the exact author, or `author_name` plus `candidate_index` after `scholarfetch_author_candidates`. Supported comma-separated `filters`: year>=YYYY, year<=YYYY, year=YYYY, has:abstract, has:doi, has:pdf, venue:<text>, title:<text>, doi:<text>. If you pass `engines`, it must include `openalex`.

  Parameters:

  • limit — integer
  • engines — string
  • filters — string
  • author_id
  • author_name
  • candidate_index — integer

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• scholarfetch_abstract

  Read the best abstract available for a paper. Use with a DOI or with author_name + candidate_index + paper_index after author_papers. If you pass `engines`, use a comma-separated subset of: elsevier, openalex, crossref, arxiv, europepmc, springer, semanticscholar.

  Parameters:

  • doi
  • engines — string
  • author_name
  • paper_index — integer
  • candidate_index — integer

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• scholarfetch_article_text

  Read full paper text when machine-readable content is recoverable. Use with a DOI or with author_name + candidate_index + paper_index. Uses Elsevier first, then open-access fallbacks such as Springer OA, Europe PMC, arXiv PDF, and generic PDF URLs when text is recoverable. If you pass `engines`, use a comma-separated subset of: elsevier, openalex, crossref, arxiv, europepmc, springer, semanticscholar.

  Parameters:

  • doi
  • engines — string
  • author_name
  • paper_index — integer
  • candidate_index — integer

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• scholarfetch_references

  Expand a paper into its references. Use with a DOI or with author_name + candidate_index + paper_index. This is the main edge-expansion tool for traversing the literature graph. If you pass `engines`, use a comma-separated subset of: elsevier, openalex, crossref, arxiv, europepmc, springer, semanticscholar.

  Parameters:

  • doi
  • engines — string
  • author_name
  • paper_index — integer
  • candidate_index — integer

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• scholarfetch_saved_add

  Add one paper to a named in-memory reading list on the MCP server. Best input is paper_json copied from another ScholarFetch tool result, but DOI, query+result_index, or author_name+candidate_index+paper_index also work. Reuse the same collection name across calls to keep one research session together.

  Parameters:

  • doi
  • query
  • engines — string
  • collection — string
  • paper_json
  • author_name
  • paper_index — integer
  • result_index — integer
  • candidate_index — integer

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• scholarfetch_saved_list

  List all papers currently saved in a named in-memory reading list. Use this to inspect the working set before exporting or removing items.

  Parameters:

  • collection — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• scholarfetch_saved_remove

  Remove one paper from a named in-memory reading list by DOI or exact title.

  Parameters:

  • doi
  • title
  • collection — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• scholarfetch_saved_clear

  Clear all papers from a named in-memory reading list. Useful when restarting a research branch.

  Parameters:

  • collection — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• scholarfetch_saved_export

  Export the current reading list as citations, abstracts, BibTeX, or an aggregated full-text corpus. Valid `format` values: citations, abstracts, bib, fulltext. Valid `style` values when `format=citations`: harvard, apa, ieee. Use `include_references=true` with `format=fulltext` when you want a richer downstream synthesis corpus.

  Parameters:

  • style — string
  • format — string
  • engines — string
  • collection — string
  • include_references — boolean

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.