claude-scholar

MCP server · GitHub · ★ 5.9k · graded 2026-10-21Source linked

Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication.

No outside reports on file

Only use claude-scholar with non-sensitive research and code; never process confidential data, unpublished findings, or proprietary information.

Based on public adoption and transparency signals as of Oct 21, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Claude Scholar helpful?

What it can access

Local filesNo local folder access notedLOW
Command executionNo shell command runner notedLOW
Network reachConnects to outside service APINOTED
CredentialsNo API token requiredLOW
Package sourceGitHub (Galaxy-Dawn/claude-scholar)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/Galaxy-Dawn/claude-scholar ↗

All setup options ↓

Check this skill Watch it in my stack Compare README badge View project

Everything known

We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.

0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30

Popularity grade: B (from public signals such as stars and downloads, not a code review). Graded 2026-10-21.

Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.

Check a specific version →

About Claude Scholar

Claude-scholar is a research helper that connects Claude AI to tools for academic work and coding projects. It helps with planning research, writing code, running experiments, and preparing papers for publication.

Who it’s for

Researchers, students, and software developers who want AI assistance throughout the research and development process. It's designed for people using Claude through different coding interfaces.

Alternatives

Elicit: AI research paper search and summarization tool
Consensus: Finds research backed by scientific evidence
Perplexity AI: General-purpose research assistant with academic sources
Connected Papers: Visualizes academic paper relationships and citations

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README at https://github.com/Galaxy-Dawn/claude-scholar (opens external site) for installation steps, as this is a specialized research tool with multiple integration points.

Why this grade

BB — Some risk signals

Signal-based grade (4/7 points): very widely starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

41/100

GitHub stars: 5.9k
Listing last refreshed: 2026-10-29

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Risks to watch for

Accidental data sharing: Research papers, code, or experiment results could be sent to Claude's servers during analysis
Credential exposure: API keys or authentication tokens for academic databases might leak if stored insecurely
Misleading sources: The tool could direct you to fake research papers or altered code repositories through social engineering
Incomplete citations: AI-generated research summaries might misattribute sources or invent references that sound real
Network access: It may connect to external academic databases or services, creating paths for data exfiltration

How to lower the risk

Least-privilege permissions

Run it in a sandboxed environment separate from production systems
Limit file access to specific project folders only

Network isolation

Monitor outbound connections to ensure it only reaches intended academic services
Use a firewall rule to block unexpected external requests

Monitoring

Log all data sent to Claude and external APIs
Review what files and repositories the tool accesses

Red flags to watch for

Unexpected connections to unfamiliar IP addresses or domains
Requests for credentials or API keys that shouldn't be needed
Large data transfers to cloud services

Questions

How do I install Claude Scholar?

Claude Scholar does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/Galaxy-Dawn/claude-scholar.

Are there security reports about Claude Scholar?

No reports found for this package in our research (last checked 2026-10-30). Claude Scholar currently holds Grade B (Some risk signals) based on public adoption and transparency signals. Key risk areas to watch include accidental data sharing, credential exposure, misleading sources.

Is Claude Scholar actively maintained?

Claude Scholar has 5.9k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/Galaxy-Dawn/claude-scholar before pinning it in production.

What are alternatives to Claude Scholar?

Notable alternatives to Claude Scholar include Elicit (AI research paper search and summarization tool), Consensus (Finds research backed by scientific evidence), Perplexity AI (General-purpose research assistant with academic sources), Connected Papers (Visualizes academic paper relationships and citations). You can also compare Claude Scholar side by side with other MCP servers in the Related tools section on this page.

Maintain or use Claude Scholar? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

AgentArmorHQ Risk Grade B for Claude Scholar

GitHub README Markdown:

markdown

[![AgentArmorHQ Risk Grade for Claude Scholar](https://agentarmorhq.com/api/badge/galaxy-dawn-claude-scholar)](https://agentarmorhq.com/skills/galaxy-dawn-claude-scholar)

HTML embed:

html

<a href="https://agentarmorhq.com/skills/galaxy-dawn-claude-scholar"><img src="https://agentarmorhq.com/api/badge/galaxy-dawn-claude-scholar" alt="AgentArmorHQ Risk Grade for Claude Scholar" height="20" /></a>

Terminal check:

terminal

curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "galaxy-dawn-claude-scholar"

Share with your security lead

Need sign-off to use claude-scholar? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: claude-scholar
- **Listing URL:** https://agentarmorhq.com/skills/galaxy-dawn-claude-scholar
- **Type:** App connector
- **Risk Grade:** Grade B (Some risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 5.9k GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (Galaxy-Dawn/claude-scholar)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/Galaxy-Dawn/claude-scholar
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 21, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type: App connector
Publisher: Galaxy-Dawn
Source code: github.com/Galaxy-Dawn/claude-scholar
Est. context load: ~900 tokens / turn (~5 tool schemas, 0.45% of 200k context)
Popularity: 5.9k GitHub stars
Last updated: 2026-10-29
Last graded: 2026-10-21

Community

Discussions for Claude Scholar

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for Claude Scholar helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude