Academic Paper Search MCP服务器
Multi-Source Academic Paper Retrieval and Metadata Integration Tool
Install & Use
Copy this prompt and send it to your AI assistant (Claude / Cursor / TRAE / Codex / WorkBuddy etc.) to auto-install:
Help me install this AI Skill: Academic Paper Search MCP服务器. It is used for: Multi-Source Academic Paper Retrieval and Metadata Integration Tool Full Skill content: https://321skill.com/skills/academic-paper-search/raw/index.md Read that page and install it.
The prompt includes a link to the full Skill content. You can also view the full content.
This Skill addresses the inefficiency of academic paper retrieval. In practice, researchers and students often need to search for papers across multiple databases (e.g., Crossref, Semantic Scholar), and manually switching platforms and copying results is time-consuming. This tool, via a unified MCP interface, enables AI assistants to directly invoke multi-source search, fetch metadata, and obtain full-text links.
Usage is simple: you just need to install it via Smithery with one click and configure your API Key (optional). After that, you can search for papers, get details, or filter by topic using natural language instructions, such as 'Help me search for 5 review papers about Transformer from 2024.' It will automatically call the search_papers or search_by_topic tool, returning formatted information like title, authors, abstract, and DOI.
It is ideal for teams or individuals who need to quickly retrieve academic literature, especially researchers, university students, or data analysts already using Claude Desktop as their AI assistant. For projects requiring extensive literature review, this tool can significantly reduce the time spent on manual searching and organization.
It is recommended to use this tool consistently when writing papers, conducting literature reviews, or performing technical research. Note that it primarily relies on public academic APIs; some full-text PDFs may need to be obtained separately. It is also recommended to configure a Semantic Scholar API Key to access more complete metadata (e.g., TL;DR summaries).
Key Features
Compared to directly using the Semantic Scholar API, this Skill integrates into the AI assistant workflow via the MCP protocol, supporting simultaneous multi-source (Crossref + Semantic Scholar) search without the need to manually write HTTP requests and parse JSON. It also provides filtering by year and topic, making it more aligned with research scenarios.
Limitations
Requires the Python and uv toolchain and network access. Default search results are limited to 10 items, and some full-text PDFs may not be directly accessible due to copyright restrictions.
FAQ
Which paper sources are supported?
Currently supports two sources: Crossref and Semantic Scholar. You can specify which source to use via parameters.
Do I need to apply for an API Key?
A Semantic Scholar API Key is optional, but configuring it allows access to richer metadata (e.g., TL;DR summaries). A Crossref API Key is also optional but recommended.
Installation guide for AI assistants
If your AI coding assistant (Claude Code, Cursor, TRAE etc.) can see this page, send it this message to auto-install:
Visit https://321skill.com/skills/academic-paper-search/raw/index.md to read the original Skill definition (Markdown format) for Academic Paper Search MCP服务器, and install it according to the instructions.
Raw Markdown URL for AI: /skills/academic-paper-search/raw/index.md