Skip to content

ScholarFetch MCP server

io.github.laibniz/scholarfetchlaibnizstreamable-httpv0.2.1Scanned

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

12 tools: 1 can delete or cancel things, 7 change things and 4 only read.

Tools: 1 delete, 0 irreversible, 7 write, 4 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the ScholarFetch MCP server can do

The ScholarFetch MCP server is published by the GitHub account laibniz. It has 12 tools. It can delete or cancel things (1 tool: scholarfetch_saved_remove) and create or change data (7 tools: scholarfetch_search, scholarfetch_author_candidates, scholarfetch_author_papers, scholarfetch_references and 3 more). 4 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 20, 2026, version 0.2.1.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

12 tools

Deletes or cancels 1Claude Code: deny
  • scholarfetch_saved_removeRemove one paper from a named in-memory reading list by DOI or exact title.No findings

    Why it is in this group

    • The name "scholarfetch_saved_remove" says "remove": a word for removing or ending something.
    Description, as the server wrote it
    Remove one paper from a named in-memory reading list by DOI or exact title.
Changes things 7Claude Code: ask
  • scholarfetch_author_candidatesDisambiguate a human author name into ranked identity candidates.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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`.
  • scholarfetch_author_papersExpand one author into a deduplicated paper list.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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`.
  • scholarfetch_referencesExpand a paper into its references.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.
  • scholarfetch_saved_addAdd one paper to a named in-memory reading list on the MCP server.No findings

    Why it is in this group

    • The name "scholarfetch_saved_add" says "add": a word for a change.
    Description, as the server wrote it
    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.
  • scholarfetch_saved_clearClear all papers from a named in-memory reading list.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Clear all papers from a named in-memory reading list. Useful when restarting a research branch.
  • scholarfetch_saved_exportExport the current reading list as citations, abstracts, BibTeX, or an aggregated full-text corpus.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.
Only reads 4Show 4 read-only tools
  • scholarfetch_abstractRead the best abstract available for a paper.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    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.
  • scholarfetch_article_textRead full paper text when machine-readable content is recoverable.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    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.
  • scholarfetch_doi_lookupEnrich one known DOI with metadata, reading links, and full-text availability signals.No findings

    Why it is in this group

    • The name "scholarfetch_doi_lookup" says "lookup": a word for reading.
    Description, as the server wrote it
    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.
  • scholarfetch_saved_listList all papers currently saved in a named in-memory reading list.No findings

    Why it is in this group

    • The name "scholarfetch_saved_list" says "list": a word for reading.
    Description, as the server wrote it
    List all papers currently saved in a named in-memory reading list. Use this to inspect the working set before exporting or removing items.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:07 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
8
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 8 tools that change things (1 destructive, 7 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://laibniz-scholarfetch-web.hf.space/mcp/: tools/list returned 12 tools to an anonymous client, including scholarfetch_saved_remove (destructive), scholarfetch_search (write), scholarfetch_author_candidates (write), scholarfetch_author_papers (write), scholarfetch_references (write) and 3 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 0.2.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http scholarfetch https://laibniz-scholarfetch-web.hf.space/mcp/
claude mcp add --transport http scholarfetch https://laibniz-scholarfetch-web.hf.space/mcp/

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__scholarfetch__scholarfetch_doi_lookup",
      "mcp__scholarfetch__scholarfetch_abstract",
      "mcp__scholarfetch__scholarfetch_article_text",
      "mcp__scholarfetch__scholarfetch_saved_list"
    ],
    "ask": [
      "mcp__scholarfetch__scholarfetch_search",
      "mcp__scholarfetch__scholarfetch_author_candidates",
      "mcp__scholarfetch__scholarfetch_author_papers",
      "mcp__scholarfetch__scholarfetch_references",
      "mcp__scholarfetch__scholarfetch_saved_add",
      "mcp__scholarfetch__scholarfetch_saved_clear",
      "mcp__scholarfetch__scholarfetch_saved_export"
    ],
    "deny": [
      "mcp__scholarfetch__scholarfetch_saved_remove"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as scholarfetch. Review it before you use it.

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.laibniz/scholarfetch/verify?hash=53c0da64a66012c9fc99e12914ec050d6eb331d2ac4f5d9cf546131631500684" | jq -e '.changed == false'

Pinned hash 53c0da64a660, from Nov 20, 2026, 01:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.laibniz/scholarfetch/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.laibniz/scholarfetch
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.laibniz/scholarfetch.svg)](https://radar.anlyon.com/servers/io.github.laibniz/scholarfetch)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:38 UTC.

ScholarFetch MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the ScholarFetch MCP server safe?

No scan can promise that. What its definitions show: 12 tools, 8 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the ScholarFetch MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: scholarfetch_saved_remove.

Can the ScholarFetch MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the ScholarFetch MCP server have?

12 tools: 1 destructive, 7 write, 4 read. scholarfetch_saved_remove, scholarfetch_search, scholarfetch_author_candidates, scholarfetch_author_papers, scholarfetch_references, scholarfetch_saved_add, scholarfetch_saved_clear, scholarfetch_saved_export and 4 more.

Does the ScholarFetch MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the ScholarFetch MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the ScholarFetch MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.