Scholar MCP
PYPI · SCHOLAR-MCP
Federated academic search, citation traversal, persistent PDF download, and temporary reading.
Available components
Last scanned (2 hours ago)
Scores higher than 88% of PyPI servers
Category Education and Research
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 Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 4 of 55 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 2 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability80
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1024 tokens (~146/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 Management100
- No destabilizing schema changes in the last 30 days.Pass
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
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.
- 5 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 3 Nov 26 0
- Package version: 0.8.5 → 0.9.0 functional
- 2 Nov 26 0
- Stability: 0.97 → pass security
- 1 Nov 26 0
- Stability: pass → 0.97 functional
- 30 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 29 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 28 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 26 Oct 26 0
- Stability: 0.97 → pass security
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 5 Nov 2026 · Analysed pypi/scholar-mcp@0.9.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
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 55 packages
| Packages resolved | 55 |
|---|---|
| Stale | 4 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
download_paper Download a paper PDF ~117
Keep a paper's PDF in your local research library. Resolves an accessible copy across archives and repositories. Use read_paper for temporary reading without keeping a PDF. A successful download keeps a separate copy when the version changes.
| Name | Type | Req | Description |
|---|---|---|---|
| collection | string | – | Knowledge-base collection to index the PDF in. Empty disables indexing. |
| paper_id | string | yes | Paper identifier (S2 ID, DOI, ArXiv:ID, etc.) |
| save_dir | string | – | Directory to save PDF (default: configured download directory) |
Structured output declared, but exposes no named fields.
No examples provided.
paper_info Inspect a paper and its citation neighborhood ~131
Look up a paper and trace what it builds on or what followed it. Detail includes the complete available abstract and author list. Citations are papers that cite it; references are papers it cites. Each relation list is ordered by citation count and limited separately.
| Name | Type | Req | Description |
|---|---|---|---|
| include | string | – | Comma-separated: detail, citations, references, data. data explicitly looks up scientific database associations. |
| limit | integer | – | Max citations/references to return (default 20) |
| paper_id | string | yes | Paper identifier (S2 ID, DOI, ArXiv:ID, OpenAlex W-ID, etc.) |
Structured output declared, but exposes no named fields.
No examples provided.
read_paper Read a paper's main text or a page range ~230
Read a paper's text, inspect figures and tables, or jump to its appendix. Returns page-aware Markdown from pages 1-10 by default, with selectors for figures and tables. Native structured articles are used when a PDF is unavailable, with original section IDs and continuation locators. Use visual to inspect a selected item. The temporary PDF is cleaned up; use download_paper to keep a local copy.
| Name | Type | Req | Description |
|---|---|---|---|
| pages | string | – | One-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. For structured articles… |
| paper_id | string | yes | Paper identifier (S2 ID, DOI, ArXiv:ID, etc.) |
| visual | string | – | Optional 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 Recommend related papers ~114
Explore related work around a paper, including connections across topics. similar finds semantic neighbours and is the default. peers finds papers cited alongside it. kin finds papers sharing its references, including connections across topics. For direct citation lists, use paper_info.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum results (default 10) |
| paper_id | string | yes | Paper identifier (S2 ID, DOI, ArXiv:ID, OpenAlex ID, etc.) |
| relation | string | – | similar | peers | kin |
Structured output declared, but exposes no named fields.
No examples provided.
search_authors Search academic authors ~61
Find researchers and their profiles, affiliations and publication metrics. Compare returned affiliations to distinguish people with the same name.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum results (1-1000, default 5) |
| query | string | yes | Author name to search for |
Structured output declared, but exposes no named fields.
No examples provided.
search_papers Search academic papers ~355
Discover papers that answer a research question or match a remembered idea. Searches multiple sources, merges duplicates, follows citation connections, and ranks for relevance. Natural-language queries work without extra parameters. Use paper_info when you already have a paper identifier. For cross-language discovery, formulate the query in the language of the target literature, usually English for computer science and AI research.
| Name | Type | Req | Description |
|---|---|---|---|
| debug | boolean | – | Include per-source latency, provenance, and internal ranking diagnostics. |
| fields_of_study | string | – | Comma-separated fields (e.g., "Computer Science,Mathematics") |
| intent | string | – | Soft relevance focus used by reranking and expansion. Use balanced normally; alternatives are foundational, recent, survey, method, and dataset. |
| limit | integer | – | Maximum results to return (1-100, default 10) |
| min_citations | integer | – | Minimum citation count filter (default 0) |
| open_access_only | boolean | – | Only return papers with free PDF access |
| paper_types | string | – | Comma-separated types, e.g. JournalArticle,Conference,Review,Book,Dataset. CourtDecision selects case law; ClinicalTrialRegistration selects study registrations. Default: all types. |
| query | string | yes | Describe what you want to find. Titles, distinctive phrases, and natural-language questions all work. |
| sort | string | – | Hard final order. Use relevance normally; citations and date replace the reranker's ordering. |
| venue | string | – | Filter by venue (e.g., "NeurIPS", "Nature") |
| year | string | – | Filter by year or range (e.g., "2023", "2020-2024") |
Structured output declared, but exposes no named fields.
No examples provided.
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
claude mcp add liyux3-scholar-mcp -- uvx scholar-mcp
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 86 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 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 1,008 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 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Scholar MCP server under?
Scholar MCP declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.