ReferenceMCP

ReferenceMCP

An academic reference manager MCP server that enables searching papers across multiple sources, managing references locally, and formatting citations in 10,000+ styles.

Category
访问服务器

README

ReferenceMCP

Academic Reference Manager MCP server for Claude Desktop. Search papers, manage references, and format citations in 10,000+ styles.

Features

  • Search across Crossref, Semantic Scholar, OpenAlex, and PubMed
  • Save references to a local SQLite database
  • Organize with collections and tags
  • Format citations in APA, MLA, Chicago, IEEE, Harvard, and thousands more CSL styles
  • Export to BibTeX, RIS, or CSL-JSON

Installation

Using uv (Recommended)

git clone https://github.com/eduardofarina/ReferenceMCP.git
cd ReferenceMCP
uv sync

Using conda

conda env create -f environment.yml
conda activate reference-mcp
pip install -e .

Configuration

  1. Copy .env.example to .env:

    cp .env.example .env
    
  2. Edit .env with your settings (all optional but recommended):

    CONTACT_EMAIL=your@email.com
    
  3. Add the server to your MCP client config.

    Claude Desktop (%APPDATA%\Claude\claude_desktop_config.json on Windows):

    {
      "mcpServers": {
        "reference-mcp": {
          "command": "uv",
          "args": [
            "--directory",
            "<path-to-ReferenceMCP>",
            "run",
            "server.py"
          ]
        }
      }
    }
    

    Replace <path-to-ReferenceMCP> with the full path to your clone (e.g. C:\Users\You\ReferenceMCP on Windows or /home/you/ReferenceMCP on Linux/macOS).

    Cursor (.cursor/mcp.json): use the same command and args, with your project path in --directory.

Available Tools

Search Tools

Tool Description
search_papers Search across sources by query
search_by_doi Look up a paper by DOI
get_paper_details Get full metadata for a saved reference
get_citations Get papers that cite a given paper
get_references Get papers cited by a given paper

Library Management

Tool Description
save_reference Save a paper by DOI
list_references List saved references
delete_reference Remove a reference
create_collection Create a collection
add_to_collection Add reference to collection
tag_reference Add tags to a reference
list_collections List all collections
list_tags List all tags

Citation Formatting

Tool Description
format_citation Format a reference in a style
format_bibliography Format multiple references
list_styles List available styles
set_default_style Set default citation style

Export

Tool Description
export_bibtex Export as BibTeX
export_ris Export as RIS
export_csl_json Export as CSL-JSON

Example Usage

User: "Find papers about transformer architectures and save the top result"

Claude:

  1. Searches with search_papers(query="transformer architectures")
  2. Saves with save_reference(doi="10.48550/arXiv.1706.03762")

User: "Format my saved papers as an APA bibliography"

Claude:

  1. Lists with list_references()
  2. Formats with format_bibliography(reference_ids=[1,2,3], style="apa")

Testing

Test with MCP Inspector:

uv run mcp dev server.py

Citation Styles

Popular styles included:

  • APA (7th Edition)
  • MLA (9th Edition)
  • Chicago (Author-Date & Notes-Bibliography)
  • IEEE
  • Harvard
  • Vancouver
  • Nature, Science, Cell
  • And 10,000+ more from the CSL repository

Data Storage

References are stored in data/references.db (SQLite). Citation styles are cached in styles/.

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选