Skip to main content

🎓 MCP Scholar

An Academic Research & Literature Analysis Server Built on the Model Context Protocol (MCP)
基于模型上下文协议(MCP)的学术文献检索与分析服务

Python Version MCP SDK Package Manager License: MIT

English | 简体中文


🌍 English

Overview

MCP Scholar (mcp-scholar) is a lightweight, extensible Model Context Protocol (MCP) server designed for academic researchers and AI agents. It empowers MCP-compatible clients—such as Claude Desktop, Claude Code, Cursor, and Cherry Studio—to search academic literature across multiple sources (OpenAlex primary + Google Scholar fallback), inspect paper details and references, analyze researcher profiles, and verify citations directly within conversational or agentic workflows.

✨ Key Features (v0.3.0)

  • 🔎 Unified Multi-Source Search: Single search_papers tool with strategy control (exact / adaptive / hybrid). OpenAlex as primary structured source, Google Scholar as fallback.
  • 📄 Deep Paper Inspection: Retrieve comprehensive metadata, full abstracts, and reference lists.
  • 👨‍🔬 Scholar Profile Analytics: Parse author profiles for high-impact publications.
  • ✅ BibTeX Verification: Cross-check and enrich BibTeX entries against Crossref/OpenAlex.
  • 🔌 MCP Tool Annotations: Read-only tools marked with readOnlyHint / idempotentHint for safer auto-approval in clients.
  • ⚡ Zero-friction Execution: uvx mcp-scholar ready.

🛠️ Available Tools

Tool Name Description Key Parameters
search_papers Unified literature search (replaces old scholar_search + adaptive_search) keywords, count, strategy (exact|adaptive|hybrid), sort_by, year_start, year_end
paper_detail Fetch detailed metadata and full abstract paper_id
paper_references Extract references / citing papers paper_id, count
profile_papers Analyze author profile and top papers profile_url / user_id, count
verify_bibtex Verify and enrich BibTeX entries bibtex
health_check Check server and upstream availability None

Legacy tools (scholar_search, adaptive_search, summarize_papers) remain available for compatibility but are deprecated in favor of the unified tools + host-model prompts.

🚀 Installation & Quick Start

uvx mcp-scholar

Or from source:

git clone https://github.com/renyumeng1/mcp_scholar.git
cd mcp_scholar
uv sync
uv run mcp-scholar

⚙️ Client Configuration

{
  "mcpServers": {
    "mcp-scholar": {
      "command": "uvx",
      "args": ["mcp-scholar"]
    }
  }
}

🗺️ Roadmap (beyond v0.3.0)

  • Full multi-source federation (Semantic Scholar, Crossref, arXiv, DBLP)
  • Preprint ↔ published deduplication
  • OA PDF section-aware parsing (Methodology / Experiments)
  • Citation intent analysis & bridge papers
  • Zotero integration
  • Local SQLite cache with TTL

🇨🇳 简体中文

项目简介

MCP Scholar(mcp-scholar)是基于 模型上下文协议(MCP) 的学术文献检索与分析服务端。它可无缝接入 Claude Desktop、Claude Code、Cursor、Cherry Studio 等客户端,支持多源学术检索、论文详情与引文溯源、学者主页分析以及 BibTeX 真实性核查。

✨ 核心特性 (v0.3.0)

  • 🔎 统一多源检索:search_papers 工具支持 exact / adaptive / hybrid 策略。OpenAlex 为主力结构化源,Google Scholar 为 fallback。
  • 📄 单篇详情与引文:完整元数据、摘要与参考文献。
  • 👨‍🔬 学者主页分析:提取高被引代表作。
  • ✅ BibTeX 核查:通过 Crossref/OpenAlex 核验并补全文献信息。
  • 🔌 MCP 工具注解:只读工具带有 readOnlyHint 等标准注解,客户端可更安全地自动放行。
  • ⚡ 一键启动:uvx mcp-scholar。

🛠️ 工具列表

工具名称 功能说明 核心参数
search_papers 统一学术检索(替代旧的 scholar_search + adaptive_search) keywords, count, strategy, sort_by, year_start, year_end
paper_detail 获取单篇论文详细信息 paper_id
paper_references 获取引用/参考文献 paper_id, count
profile_papers 分析学者主页高引论文 profile_url, count
verify_bibtex 核验并补全 BibTeX bibtex
health_check 健康检查 无

旧工具仍保留以兼容,但推荐使用新统一工具 + 宿主模型提示词完成总结。

🚀 安装

uvx mcp-scholar

🗺️ 演进路线图

  • 完整多源联邦(Semantic Scholar、Crossref、arXiv、DBLP)
  • 预印本与正式版自动对齐
  • OA PDF 分章节解析
  • 引用意图分析
  • Zotero 联动
  • 本地 SQLite 缓存

📄 许可证

本项目基于 MIT License 开源。

Metadata

Release files for mcp_scholar 0.4.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for mcp_scholar 0.4.0
File Size Uploaded Provenance
mcp_scholar-0.4.0.tar.gz 80.1 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for mcp_scholar 0.4.0
File Interpreter ABI Platform
mcp_scholar-0.4.0-py3-none-any.whl Python 3 none any Details

Total release size: 100.6 kB

Release files / mcp_scholar-0.4.0.tar.gz

Download URL mcp_scholar-0.4.0.tar.gz
Size 80.1 kB
Tags Source
SHA-256 checksum
How to use checksums
ac3642f34992607078904f50e52ab61c3d6964ee233fba98d3633776102247c6
BLAKE2b-256 checksum
How to use checksums
fae283366b2422e72e345f720a88a27f8dff2d5f14bddca2b730277f4fdef4f3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via uv/0.13.6 {"installer":{"name":"uv","version":"0.13.6","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / mcp_scholar-0.4.0-py3-none-any.whl

Download URL mcp_scholar-0.4.0-py3-none-any.whl
Size 20.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
bd2cc2fb35a7efc652546d253edcca719ebc30d22343b483ea9f11640cc3e48a
BLAKE2b-256 checksum
How to use checksums
52c6ba17666e5ec2851abacfadd0ccfaedeae7f6ca77a024b1c3e6a7ea174430
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via uv/0.13.6 {"installer":{"name":"uv","version":"0.13.6","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Security for mcp_scholar 0.4.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page