Skip to main content
Glama
Academic Paper Search MCP Server

Academic Paper Search MCP Server

by afrise

学术论文搜索 MCP 服务器

铁匠徽章

模型上下文协议 (MCP)服务器,可从多个来源搜索和检索学术论文信息。

该服务器为 LLM 提供:

  • 实时学术论文搜索功能

  • 访问论文元数据和摘要

  • 能够检索可用的全文内容

  • 遵循 MCP 规范的结构化数据响应

虽然 MCP 规范主要设计用于与 Anthropic 的 Claude Desktop 客户端集成,但它允许与支持工具/函数调用功能(例如 OpenAI 的 API)的其他 AI 模型和客户端兼容。

注意:本软件正在积极开发中。特性和功能可能会有所变更。

特征

该服务器公开以下工具:

  • search_papers :跨多个来源搜索学术论文

    • 参数:

      • query (str):搜索查询文本

      • limit (int,可选):返回的最大结果数(默认值:10)

    • 返回:包含论文详细信息的格式化字符串

  • fetch_paper_details :检索特定论文的详细信息

    • 参数:

      • paper_id (str): 论文标识符(DOI 或 Semantic Scholar ID)

      • source (str,可选):数据源(“crossref”或“semantic_scholar”,默认值:“crossref”)

    • 返回:带有全面论文元数据的格式化字符串,包括:

      • 标题、作者、年份、DOI

      • 地点、开放获取状态、PDF URL(仅限 Semantic Scholar)

      • 摘要和 TL;DR 摘要(如有)

  • search_by_topic :按主题搜索论文,可选日期范围过滤器

    • 参数:

      • topic (str):搜索查询文本(限制为 300 个字符)

      • year_start (int,可选):日期范围的开始年份

      • year_end (int,可选):日期范围的结束年份

      • limit (int,可选):返回的最大结果数(默认值:10)

    • 返回:包含搜索结果的格式化字符串,包括:

      • 论文标题、作者和年份

      • 摘要和 TL;DR 摘要(如有)

      • 场地和开放信息

Related MCP server: Academic Paper Search MCP Server

设置

通过 Smithery 安装

要通过Smithery自动为 Claude Desktop 安装 Academic Paper Search Server:

npx -y @smithery/cli install @afrise/academic-search-mcp-server --client claude

***请注意,***这种方法基本上未经测试,因为他们的服务器似乎有问题。您可以按照独立的说明进行操作,直到 smithery 得到修复。

通过 uv 安装(手动安装):

  1. 安装依赖项:

uv add "mcp[cli]" httpx
  1. 在您的环境或.env文件中设置所需的 API 密钥:

#  These are not actually implemented
SEMANTIC_SCHOLAR_API_KEY=your_key_here 
CROSSREF_API_KEY=your_key_here  # Optional but recommended
  1. 运行服务器:

uv run server.py

与 Claude Desktop 一起使用

  1. 将服务器添加到您的 Claude Desktop 配置( claude_desktop_config.json ):

{
  "mcpServers": {
    "academic-search": {
      "command": "uv",
      "args": ["run ", "/path/to/server/server.py"],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "your_key_here",
        "CROSSREF_API_KEY": "your_key_here"
      }
    }
  }
}
  1. 重启Claude桌面

发展

该服务器使用以下方式构建:

  • Python MCP SDK

  • FastMCP 简化服务器实现

  • API 请求的 httpx

API 源

  • 语义学者API

  • Crossref API

执照

本项目采用 GNU Affero 通用公共许可证 v3.0 (AGPL-3.0) 授权。该许可证确保:

  • 您可以自由使用、修改和分发本软件

  • 任何修改都必须在同一许可证下开源

  • 任何使用该软件提供网络服务的人都必须提供源代码

  • 允许商业使用,但软件及其衍生品必须保持免费和开源

请参阅LICENSE文件以获取完整的许可证文本。

贡献

欢迎贡献!您可以通过以下方式提供帮助:

  1. 分叉存储库

  2. 创建功能分支( git checkout -b feature/amazing-feature )

  3. 提交您的更改( git commit -m 'Add amazing feature' )

  4. 推送到分支( git push origin feature/amazing-feature )

  5. 打开拉取请求

请注意:

  • 遵循现有的代码风格和约定

  • 为任何新功能添加测试

  • 根据需要更新文档

  • 确保您的更改符合 AGPL-3.0 许可条款

通过对此项目做出贡献,您同意您的贡献将根据 AGPL-3.0 许可证进行授权。

Available Tools

3 tools
fetch_paper_detailsB

Get detailed information about a specific paper.

Args:
    paper_id: Paper identifier (DOI for Crossref, paper ID for Semantic Scholar)
    source: Source database ("semantic_scholar" or "crossref")

Inputs: paper_id (required), source.

search_by_topicB

Search for papers by topic with optional date range.

Note: Query length is limited to 300 characters. Longer queries will be automatically truncated.

Args:
    topic (str): Search query (max 300 chars)
    year_start (int, optional): Start year for date range
    year_end (int, optional): End year for date range  
    limit (int, optional): Maximum number of results to return (default 10)
    
Returns:
    str: Formatted search results or error message

Inputs: topic (required), limit, year_end, year_start.

search_papersC

Search for papers across multiple sources.

args: 
    query: the search query
    limit: the maximum number of results to return (default 10)

Inputs: query (required), limit.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.8/5.0

    Scored across 3 tools

    Disambiguation2/5

    The tools 'search_by_topic' and 'search_papers' have significant overlap in purpose—both search for papers, with only minor differences in parameters. This creates ambiguity, as an agent might struggle to choose between them. The 'fetch_paper_details' tool is distinct, but the two search tools are not clearly differentiated.

    Naming Consistency3/5

    The naming is mixed: 'fetch_paper_details' uses a verb_noun pattern, while 'search_by_topic' and 'search_papers' use verb_preposition_noun and verb_noun styles, respectively. This inconsistency makes the set less predictable, though the names are still readable and descriptive.

    Tool Count2/5

    With only 3 tools, the server feels thin for an academic paper search domain. It lacks essential operations like filtering by author, journal, or citation count, and there's no update or delete functionality, which limits its utility for comprehensive paper management.

    Completeness2/5

    The tool surface is incomplete for academic paper search. It covers basic fetch and search operations but misses key features such as author-based searches, citation tracking, paper categorization, or integration with reference managers. This will likely cause agent failures in complex workflows.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      A
      maintenance
      Enables LLMs and compatible clients to search academic papers and retrieve detailed metadata, abstracts, and full-text content when available from Semantic Scholar and Crossref. Supports topic-based searches with optional date ranges and structured responses for tool/function calling.
      -
    • F
      license
      Not graded
      quality
      A
      maintenance
      Enables LLMs to search academic papers across Semantic Scholar and Crossref, fetch detailed metadata and abstracts by DOI or paper ID, and filter topic searches by publication year. Results are returned as structured responses usable for natural-language research queries.
      -
    • F
      license
      Not graded
      quality
      A
      maintenance
      Enables searching and retrieving academic paper information from Semantic Scholar and Crossref, including metadata, abstracts, full-text when available, and topic/date-range searches.
      -