authorprofilemcp

Name: authorprofilemcp
Rating: 0.1 (2 reviews)
Author: alperenkocyigit

搜索与获取

by alperenkocyigit

发现研究者的合作者与协作网络，从 scholar 档案提取研究兴趣和关键词，助力文献综述与团队遴选。

2GitHub

什么是 authorprofilemcp？

发现研究者的合作者与协作网络，从 scholar 档案提取研究兴趣和关键词，助力文献综述与团队遴选。

核心功能 (2 个工具)

get_coauthors

Get all co-authors for a given author. Args: name: Author's first name surname: Author's last name institution: Optional institution affiliation field: Optional research field Returns: Dictionary containing co-authors list with their information

get_author_keywords

Get research keywords/areas for a given author from Google Scholar. Args: name: Author's first name surname: Author's last name institution: Optional institution affiliation Returns: Dictionary containing keywords extracted from Google Scholar

README

Academic Author Network MCP Server

A Model Context Protocol (MCP) server for analyzing academic author networks and research collaborations.

Features

get_coauthors: Find all co-authors for a given researcher
get_author_keywords: Extract research keywords from Google Scholar profile

Installation

Clone or download this repository

Create a virtual environment:

bash

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

Install dependencies:
bash
```
pip install -r requirements.txt
```

Usage

Running the Server

bash

python server.py

Example Tool Calls

Finding Co-authors

python

result = await get_coauthors(
    name="Yann", 
    surname="LeCun",
    institution="NYU"  # Optional
)

Getting Research Keywords from Google Scholar

python

keywords = await get_author_keywords(
    name="Yann",
    surname="LeCun"
)

Data Sources

The server uses:

Semantic Scholar API: Primary source for author and publication data
OpenAlex API: Open academic knowledge graph
Crossref API: DOI resolution and metadata
Google Scholar: Web scraping for research interests and keywords

Features

Rate Limiting: Respects API rate limits and includes delays for web scraping
Caching: Reduces redundant API calls and scraping requests
Error Handling: Graceful handling of API failures and scraping issues
Data Merging: Combines data from multiple sources for co-authors
Async Operations: Parallel API requests for better performance

Configuration

The server includes built-in rate limiting and error handling. No additional configuration is required for basic usage.

Limitations

Free tier API limits apply
Google Scholar scraping includes respectful delays
Results quality depends on author name uniqueness
Web scraping may occasionally fail due to anti-bot measures

Contributing

Contributions are welcome! Please ensure all API integrations respect rate limits and terms of service.

常见问题