Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Scholar MCP

PYPI · SCHOLAR-MCP · SCANNED SEP 20

Federated academic search, citation traversal, persistent PDF download, and temporary reading.

Available components

+3 this week 62 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security50
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 1 of 43 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency35
Schema Quality & AI Usability82
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1366 tokens (~195/item across 7 items; 6 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management50
  • Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Scholar MCP server?

Scholar MCP runs locally as a PyPI package, launched with uvx scholar-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · scholar-mcp

# add to Claude Code
claude mcp add liyux3-scholar-mcp -- uvx scholar-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "liyux3-scholar-mcp": {
      "command": "uvx",
      "args": [
        "scholar-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "liyux3-scholar-mcp": {
      "command": "uvx",
      "args": [
        "scholar-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add liyux3-scholar-mcp -- uvx scholar-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "liyux3-scholar-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "scholar-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add liyux3-scholar-mcp --command uvx --arg scholar-mcp
# ~/.hermes/config.yaml
mcp_servers:
  liyux3-scholar-mcp:
    command: "uvx"
    args: ["scholar-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "liyux3-scholar-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "scholar-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add liyux3-scholar-mcp -t stdio -c uvx -a scholar-mcp
// mcp.json
{
  "mcpServers": {
    "liyux3-scholar-mcp": {
      "command": "uvx",
      "args": [
        "scholar-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 −15
    • Malware scan: pass → unverified security
  • 16 Sept 26 +16
    • Malware scan: unverified → pass security
  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +3
    • Stability: unverified → 0.23 functional
  • 5 Sept 26 55

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed pypi/scholar-mcp@0.8.4

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted setuptools.build_meta

Background: Why install scripts are a supply-chain risk →

Dependencies 43 packages
Packages resolved 43
Stale 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~1,350 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
download_paper ~182

Resolve one paper to an open-access PDF and save it to disk, optionally indexing it into a library collection. Writes a file under save_dir (default: the configured papers directory); a repeat call for the same paper overwrites the same path. Use read_paper instead when you only need the text once. Resolution tries the canonical archive (arXiv, Europe PMC), repository resolvers, preprint servers and Unpaywall in order; a paywalled paper with no open copy returns a clear failure and writes nothing.

NameTypeReqDescription
collectionstringKnowledge-base collection to index the PDF in. Empty disables indexing.
paper_idstringyesPaper identifier (S2 ID, DOI, ArXiv:ID, etc.)
save_dirstringDirectory to save PDF (default: configured download directory)

Structured output declared, but exposes no named fields.

No examples provided.

paper_info ~174

Get metadata for one known paper, optionally with the papers that cite it and the papers it references. Use this when you already have an identifier; use search_papers to find one first, and recommend_papers for related work that is not a direct citation. Read-only, one upstream lookup per requested section. An unresolvable identifier returns a not-found message rather than an error. Citation and reference lists are ordered by influence and cut at limit.

NameTypeReqDescription
includestringComma-separated: "detail", "citations", "references" (default: "detail")
limitintegerMax citations/references to return (default 20)
paper_idstringyesPaper identifier (S2 ID, DOI, ArXiv:ID, OpenAlex W-ID, etc.)

Structured output declared, but exposes no named fields.

No examples provided.

read_paper ~213

Fetch a paper's PDF into a temporary file and return page-aware Markdown text plus selectors for its figures and tables. Use this to read; use download_paper to keep the PDF. Nothing persists after the call. Resolution follows the same open-access chain as download_paper, so paywalled papers without an open copy fail cleanly. Pass a selector from a previous response as visual to get one figure or table with its surrounding text.

NameTypeReqDescription
pagesstringOne-indexed page range. The default usually reaches the conclusion of an AI conference paper. Use ranges such as "11-20" for appendices. At most 20 pages can be read per call.
paper_idstringyesPaper identifier (S2 ID, DOI, ArXiv:ID, etc.)
visualstringOptional selector returned by this tool, such as "Figure 3", "Table 2", or "page 5". Returns one focused visual with its text.

Structured output declared, but exposes no named fields.

No examples provided.

recommend_papers ~245

Find related papers by a chosen citation-graph relation. Use this when you hold one paper and want its neighbourhood. Use search_papers for a topic and paper_info for a paper's direct citation lists. Read-only; results come from embedding and citation data, so very new or uncited papers return few or no neighbours. "Related" is several different questions, and which one you want depends on what you are doing: similar embedding neighbours (SPECTER2). Same topic, possibly different vocabulary. Good default. peers what is cited alongside this paper. Its intellectual cohort, which is usually what "related work" means. kin what cites the same works this paper does. Shared method rather than shared topic, so this is the relation that crosses field boundaries: two papers can be coupled without sharing any vocabulary.

NameTypeReqDescription
limitintegerMaximum results (default 10)
paper_idstringyesPaper identifier (S2 ID, DOI, ArXiv:ID, OpenAlex ID, etc.)
relationstringsimilar | peers | kin

Structured output declared, but exposes no named fields.

No examples provided.

search_authors ~120

Search for researchers by name and return profiles with affiliations, paper counts, h-index and identifiers. Use this for people, not papers: use search_papers for papers and paper_info for a paper's own author list. Read-only. Name matching is fuzzy, so common names return many candidates; add an affiliation or field word to the query and keep limit small to disambiguate.

NameTypeReqDescription
limitintegerMaximum results (1-1000, default 5)
querystringyesAuthor name to search for

Structured output declared, but exposes no named fields.

No examples provided.

search_papers ~416

Search for academic papers across many sources (OpenAlex, Semantic Scholar, arXiv, PubMed, OpenReview, Crossref and more), merge duplicates across DOI/arXiv/S2/OpenAlex identities, and rerank for relevance. Use this to find papers from a topic, a question, or a half-remembered title. Use paper_info when you already hold an identifier, recommend_papers to expand from one known paper, and search_authors for people. Read-only. Each call fans out to live APIs under a time budget; sources that time out are reported as degraded coverage instead of failing the call. Put years, venues and filters in the parameters, not in the query text.

NameTypeReqDescription
debugbooleanInclude per-source latency, provenance, and internal ranking diagnostics.
fields_of_studystringComma-separated fields (e.g., "Computer Science,Mathematics")
intentstringSoft relevance focus used by reranking and expansion. Use balanced normally; alternatives are foundational, recent, survey, method, and dataset.
limitintegerMaximum results to return (1-100, default 10)
min_citationsintegerMinimum citation count filter (default 0)
open_access_onlybooleanOnly return papers with free PDF access
paper_typesstringComma-separated types (e.g., "JournalArticle,Conference,Review,Book,Dataset"). Default: all types.
querystringyesSearch query (e.g., "attention is all you need", "CRISPR gene editing")
sortstringHard final order. Use relevance normally; citations and date replace the reranker's ordering.
venuestringFilter by venue (e.g., "NeurIPS", "Nature")
yearstringFilter by year or range (e.g., "2023", "2020-2024")

Structured output declared, but exposes no named fields.

No examples provided.

Common questions

What is the Scholar MCP server?

Scholar MCP is listed in the public MCP registry as io.github.Liyux3/scholar-mcp. Federated academic search, citation traversal, persistent PDF download, and temporary reading. This page covers its PyPI package (scholar-mcp).

Is the Scholar MCP server safe to use?

Scholar MCP scores 62 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Scholar MCP server expose?

Scholar MCP exposes 6 tools: search_papers, paper_info, recommend_papers, search_authors, download_paper, read_paper. Their descriptions and schemas cost roughly 1,350 tokens of context every time the server is loaded.

Is the Scholar MCP server still maintained?

Scholar MCP is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.