Paper Search MCP
Paper Search MCP
一个用于从多个来源搜索和下载学术论文的模型上下文协议(MCP)服务器。该项目遵循免费优先策略:优先使用开放和公共数据源,在 API 密钥能提升稳定性或覆盖范围时提供可选的 API 密钥支持,并保持特定来源的连接器可扩展,以满足高级用户需求。
目录
Related MCP server: Academic Paper MCP HTTP/SSE Server
概述
paper-search-mcp 是一个基于 Python 的工具,用于从多个平台搜索和下载学术论文。它提供搜索论文、下载 PDF 和提取文本的工具,非常适合研究人员和 AI 驱动的工作流。它可以作为 MCP 服务器(用于 Claude Desktop 和其他 MCP 客户端)使用,也可以作为带有 CLI 界面的 Claude Code 技能使用。
项目原则
免费优先:公共和开放来源是默认路线。付费或受限来源不是本项目的核心方向。
可选 API 密钥:仅当 API 密钥能提升稳定性、速率限制或元数据质量时才支持。MCP 在可能的情况下仍应无需密钥即可使用。
对 LLM 友好的检索:搜索结果应标准化、去重,并尽可能完整,以支持下游 LLM 工作流。
来源透明:不同来源各有优势。MCP 应明确说明这些权衡,而不是假装每个来源都支持全文检索。
功能特性
两层架构:
第 1 层(统一工具):高层
search_papers用于多来源并发搜索与去重,download_with_fallback依赖出版商开放获取链接并带顺序回退。第 2 层(平台连接器):针对特定学术平台(arXiv、PubMed、bioRxiv、Semantic Scholar 等)的模块化连接器,通过正则文本分析或 API 字段实现智能 DOI 提取。
多来源支持:从 arXiv、PubMed、bioRxiv、medRxiv、Google Scholar、IACR ePrint Archive、Semantic Scholar、Crossref、OpenAlex、PubMed Central (PMC)、CORE、Europe PMC、dblp、OpenAIRE、CiteSeerX、DOAJ、BASE、Zenodo、HAL、SSRN、Unpaywall(DOI 查询)以及可选的 Sci-Hub 工作流中搜索和下载论文。
标准化输出:论文通过
Paper类以一致的字典格式返回。免费优先设计:在任何可选的商业或受限集成之前,优先使用开放和公共来源。
可选 API 密钥增强:像 Semantic Scholar 这样的来源可以使用用户提供的 API 密钥获得更好的效果,但不会强制付费使用。
发现 + 检索工作流:Google Scholar 和 Crossref 可用于发现和 DOI 回填,而开放存储库和出版商链接用于在可用时进行合法的全文解析。
OA 优先回退链:
download_with_fallback现在遵循来源原生下载 → OpenAIRE/CORE/Europe PMC/PMC 发现 → Unpaywall DOI 解析 → 可选 Sci-Hub。MCP 集成:兼容 MCP 客户端,用于 LLM 上下文增强。
可扩展设计:通过扩展
academic_platforms模块,轻松添加新的学术平台。
来源策略
长期目标不是依赖单一搜索引擎,而是结合多个免费和公共来源并明确分工:
开放元数据骨干:Crossref、OpenAlex、Semantic Scholar、dblp、CiteSeerX、SSRN、Unpaywall(以 DOI 为中心的 OA 元数据)。
学科特定来源:arXiv、PubMed、PubMed Central、Europe PMC、IACR。
开放获取全文来源:arXiv、PMC、CORE、OpenAIRE、DOAJ、BASE、Zenodo、HAL、出版商开放获取链接。
发现与 DOI 恢复:当其他公共元数据来源不完整时,Google Scholar 可用于查找标题、版本和 DOI 线索。
推荐的免费优先路线图:
保持当前公共来源稳定。
添加 OpenAlex 作为广泛的免费元数据来源。
添加 PubMed Central 和 Europe PMC 以增强生物医学全文访问。
添加 CORE 和 OpenAIRE 用于基于存储库的开放获取检索。
主要将 Google Scholar 用作发现回退,而非主要规范来源。
平台能力矩阵
此矩阵反映了本仓库中功能性和端到端回归测试的已验证实时集成结果。各列显示正常条件下观察到的最高能力级别。
平台 | 搜索 | 下载 | 阅读 | 备注 |
arXiv | ✅ | ✅ | ✅ | 开放 API;稳定可靠 |
PubMed | ✅ | ❌ | ⚠️ 仅信息 | 开放 API;稳定可靠 |
bioRxiv | ✅ | ✅ | ✅ | 开放 API;稳定可靠 |
medRxiv | ✅ | ✅ | ✅ | 开放 API;稳定可靠 |
Google Scholar | ⚠️ | ❌ | ❌ | 有机器人检测;请设置 |
IACR | ✅ | ✅ | ✅ | 开放 API;稳定可靠 |
Semantic Scholar | ✅ | ✅ (OA) | ✅ (OA) | 无密钥可用(有速率限制);密钥可提升限制;密钥被拒(403)时自动无密钥重试 |
Crossref | ✅ | ❌ | ⚠️ 仅信息 | 开放 API;稳定可靠 |
OpenAlex | ✅ | ❌ | ⚠️ 仅信息 | 开放 API;稳定可靠 |
PMC | ✅ | ✅ (仅 OA) | ✅ (仅 OA) | 仅 OA PDF;某些代理环境可能阻止直接下载 |
CORE | ✅ | ✅ (取决于记录) | ✅ (取决于记录) | 建议使用免费密钥;连接器带退避重试,401/403 时回退到无密钥 |
Europe PMC | ✅ | ✅ (OA) | ✅ (OA) | 仅 OA PDF;某些代理环境可能阻止直接下载 |
dblp | ✅ | ❌ | ⚠️ 仅信息 | 开放 API;稳定可靠 |
OpenAIRE | ✅ | ❌ | ❌ | 开放 API;瞬时 403 时以递增请求配置重试 3 次 |
CiteSeerX | ⚠️ | ✅ (取决于记录) | ⚠️ | API 端点间歇性不可用 / 重定向到网络存档 |
DOAJ | ✅ | ⚠️ (取决于 URL) | ⚠️ (取决于 URL) | PDF 可用性因文章而异;免费密钥可提高速率限制 |
BASE | ⚠️ | ✅ (取决于记录) | ✅ (取决于记录) | OAI-PMH 端点需要机构 IP 注册;否则优雅地返回空结果 |
Zenodo | ✅ | ✅ (取决于记录) | ✅ (取决于记录) | 开放 API;稳定可靠 |
HAL | ✅ | ✅ (取决于记录) | ✅ (取决于记录) | 开放 API;稳定可靠 |
SSRN | ⚠️ | ⚠️ 尽力而为 | ⚠️ 尽力而为 | 403 机器人检测生效;仅公开 PDF |
Unpaywall | ✅ (DOI 查询) | ❌ | ❌ | 需要 |
Sci-Hub(可选) | ⚠️ 仅回退 | ✅ | ❌ | 可选;镜像不稳定;用户自行承担责任 |
IEEE Xplore 🔑 | 🚧 骨架 | 🚧 骨架 | 🚧 骨架 | 需要 |
ACM DL 🔑 | 🚧 骨架 | 🚧 骨架 | 🚧 骨架 | 需要 |
✅ = 实时测试中稳定可靠。⚠️ = 可用但受上游不稳定或访问限制影响。❌ = 不支持。🔑 = 需要密钥。🚧 = 仅骨架。
凭据与 API 密钥要求
除非另有说明,所有密钥均为可选。请在 ~/.config/paper-search-mcp/.env(推荐)中配置,或作为 shell 导出变量。
环境变量 | 提供方 | 是否必需? | 获取方式 |
| Unpaywall | 是(未设置则禁用 Unpaywall) | 任意有效邮箱;在 unpaywall.org 注册 |
| CORE | 推荐 | 在 core.ac.uk/services/api 免费获取 |
| Semantic Scholar | 可选 | 在 semanticscholar.org 免费获取 — 可提升速率限制 |
| Google Scholar | 可选 | 你的 HTTP/HTTPS 代理 URL — 可绕过机器人检测 |
| DOAJ | 可选 | 在 doaj.org 免费获取 — 可提高每小时速率限制 |
| Zenodo | 可选 | 在 zenodo.org 免费获取 — 访问私有记录时必需 |
| IEEE Xplore | 激活所必需 | 在 developer.ieee.org 免费获取 |
| ACM DL | 激活所必需 |
所有变量均遵循 PAPER_SEARCH_MCP_<NAME> 前缀命名方案。不带前缀的旧名称(如 CORE_API_KEY、UNPAYWALL_EMAIL)仍受支持,以保持向后兼容。
已知上游限制
某些搜索失败是由外部提供方的不稳定性造成的,而非本项目中的缺陷:
来源 | 症状 | 原因 | 解决方法 |
Google Scholar | 返回 0 条结果 / 空 HTML | 机器人检测(CAPTCHA) | 将 |
Semantic Scholar | 429 速率受限响应 | 匿名访问速率限制 | 设置 |
CORE | 500 / 超时错误 | 未认证的速率限制 | 设置 |
OpenAIRE | 瞬时 403 响应 | 基于 IP 的会话速率限制 | 连接器按配置文件重试 3 次,逐级升级:普通会话 → XML Accept 头 → 使用 Mozilla UA 的原始 |
CiteSeerX | 通过 Web 存档重定向返回 404 | PSU 端点间歇性重定向到存档 | 无解决方法;连接器优雅地返回空结果 |
BASE | 搜索返回 0 条结果 | OAI-PMH 端点需要机构 IP 注册 | 在 base-search.net 注册以获取 API 访问权限;否则连接器优雅地返回空结果 |
SSRN | HTTP 403 | 机器人检测(Cloudflare) | 无解决方法;连接器尝试两个端点,失败时返回明确消息 |
PMC / Europe PMC | PDF 下载 ProxyError | 本地代理阻止直接 HTTPS PDF 下载 | 禁用代理或改用 |
Unpaywall | 完全跳过 | 未设置 | 在 |
可选付费平台连接器(第三阶段)
IEEE Xplore 和 ACM Digital Library 连接器作为可选加入的骨架包含在内。 它们默认禁用 — 除非你显式配置相应的密钥,否则不会发起任何 API 调用。
平台 | 环境变量 | 状态 |
IEEE Xplore |
| 🚧 骨架 — 搜索已注册,下载/阅读抛出 |
ACM Digital Library |
| 🚧 骨架 — 搜索已注册,下载/阅读抛出 |
如何启用:
export PAPER_SEARCH_MCP_IEEE_API_KEY=<your_ieee_key> # free key at https://developer.ieee.org/
export PAPER_SEARCH_MCP_ACM_API_KEY=<your_acm_key> # see https://libraries.acm.org/digital-library一旦设置了密钥,相应的来源会自动添加到 ALL_SOURCES 中,其 MCP 工具(search_ieee / search_acm、download_ieee / download_acm、read_ieee_paper / read_acm_paper)会在服务器启动时注册。
未设置密钥时,连接器仅记录一条启动警告 — 服务器的其余部分不受影响。
免费来源扩展(第四阶段)
三个额外的免费来源连接器现已集成到 MCP 服务器中:
zenodo:官方 Zenodo REST API 连接器(搜索 + 依赖记录的 PDF/阅读支持)。hal:HAL 公共 API 连接器(搜索 + 依赖记录的 PDF/阅读支持)。ssrn:以发现优先的连接器,具有强化的解析器,并在存在直接公共 PDF 链接时尽力下载/阅读。unpaywall:以 DOI 为中心的开放获取元数据来源,用于独立查询(search_unpaywall)和回退 URL 解析。
SSRN 集成仍然以合规为先:它仅尝试 SSRN 页面公开的直接公共 PDF 链接。如果需要登录/受限交付,连接器会返回明确消息,而不是绕过访问控制。
Sci-Hub 声明
Sci-Hub 支持可以作为可选连接器保留,供明确选择启用它的用户使用,但不应被视为默认或推荐的全文获取路径。
可用性不稳定,镜像地址频繁变更。
法律和政策风险因司法管辖区而异。
README 和工具描述应明确说明用户有责任自行启用和使用它。
应尽可能优先尝试开放获取和出版商许可的来源。
安装
选择最适合你工作流程的方法。所有方法都支持相同的可选 API 密钥。
Claude Code(技能)— 推荐给 Claude Code 用户
作为 Claude Code 技能而非 MCP 服务器安装。这样,当你提到查找论文、学术文献等内容时,Claude 会自动获得论文搜索能力 — 无需 MCP 配置。
前置条件:uv 和 Claude Code。
第 1 步 — 安装 CLI:
uv tool install paper-search-mcp第 2 步 — 安装技能:
mkdir -p ~/.claude/skills/paper-search
curl -fsSL https://raw.githubusercontent.com/openags/paper-search-mcp/main/claude-code/SKILL.md \
-o ~/.claude/skills/paper-search/SKILL.md第 3 步(可选)— 配置 API 密钥:
创建 ~/.config/paper-search-mcp/.env 以配置可选 API 密钥(参见环境变量)。
就这样。 下次启动 Claude Code 时,直接让它查找论文 — 技能会自动激活。例如:
"帮我找一些关于 CRISPR 碱基编辑的最新论文"
"在 arxiv 和 semantic scholar 上搜索 transformer 注意力机制"
"下载 arxiv 论文 2106.12345 的 PDF"
该技能使用一个 CLI(paper-search),它封装了与 MCP 服务器相同的库,搜索/下载输出 JSON,阅读输出纯文本。
MCP 服务器配置文件位置(适用于以下方法)
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.jsonLinux:
~/.config/Claude/claude_desktop_config.json
方法 1 — Smithery(一条命令,推荐用于 Claude Desktop)
npx -y @smithery/cli install @openags/paper-search-mcp --client claudeSmithery 会自动为你写入正确的配置块。无需手动编辑 JSON。
方法 2 — uvx(无需安装,始终最新)
uvx 直接从 PyPI 运行包,无需永久安装。需要 uv。
# Install uv (skip if already installed)
curl -LsSf https://astral.sh/uv/install.sh | sh⚠️ macOS 注意:
uvx生成的包装脚本依赖realpath,而 macOS 默认不包含该命令。如果你看到realpath: command not found错误,请安装 GNU coreutils(brew install coreutils)或改用方法 3(uv run) — 该方法没有此限制。
Claude Desktop 配置:
{
"mcpServers": {
"paper-search-mcp": {
"command": "uvx",
"args": ["paper-search-mcp"],
"env": {
"PAPER_SEARCH_MCP_UNPAYWALL_EMAIL": "your@email.com",
"PAPER_SEARCH_MCP_CORE_API_KEY": "",
"PAPER_SEARCH_MCP_SEMANTIC_SCHOLAR_API_KEY": "",
"PAPER_SEARCH_MCP_ZENODO_ACCESS_TOKEN": "",
"PAPER_SEARCH_MCP_GOOGLE_SCHOLAR_PROXY_URL": "",
"PAPER_SEARCH_MCP_IEEE_API_KEY": "",
"PAPER_SEARCH_MCP_ACM_API_KEY": ""
}
}
}
}方法 3 — uv(持久安装)
uv tool install paper-search-mcpClaude Desktop 配置:
{
"mcpServers": {
"paper-search-mcp": {
"command": "uv",
"args": ["tool", "run", "paper-search-mcp"],
"env": {
"PAPER_SEARCH_MCP_UNPAYWALL_EMAIL": "your@email.com",
"PAPER_SEARCH_MCP_CORE_API_KEY": "",
"PAPER_SEARCH_MCP_SEMANTIC_SCHOLAR_API_KEY": "",
"PAPER_SEARCH_MCP_ZENODO_ACCESS_TOKEN": "",
"PAPER_SEARCH_MCP_GOOGLE_SCHOLAR_PROXY_URL": "",
"PAPER_SEARCH_MCP_IEEE_API_KEY": "",
"PAPER_SEARCH_MCP_ACM_API_KEY": ""
}
}
}
}方法 4 — pip(标准 Python 安装)
pip install paper-search-mcpClaude Desktop 配置:
{
"mcpServers": {
"paper-search-mcp": {
"command": "python",
"args": ["-m", "paper_search_mcp.server"],
"env": {
"PAPER_SEARCH_MCP_UNPAYWALL_EMAIL": "your@email.com",
"PAPER_SEARCH_MCP_CORE_API_KEY": "",
"PAPER_SEARCH_MCP_SEMANTIC_SCHOLAR_API_KEY": "",
"PAPER_SEARCH_MCP_ZENODO_ACCESS_TOKEN": "",
"PAPER_SEARCH_MCP_GOOGLE_SCHOLAR_PROXY_URL": "",
"PAPER_SEARCH_MCP_IEEE_API_KEY": "",
"PAPER_SEARCH_MCP_ACM_API_KEY": ""
}
}
}
}如果
python不在你的 PATH 中,请将其替换为完整路径(例如/usr/bin/python3或C:\Python311\python.exe)。运行which python3/where python来查找它。
方法 5 — npx(通过 Smithery CLI,无需本地 Python)
npx -y @smithery/cli run @openags/paper-search-mcpClaude Desktop 配置:
{
"mcpServers": {
"paper-search-mcp": {
"command": "npx",
"args": ["-y", "@smithery/cli", "run", "@openags/paper-search-mcp"],
"env": {
"PAPER_SEARCH_MCP_UNPAYWALL_EMAIL": "your@email.com",
"PAPER_SEARCH_MCP_CORE_API_KEY": "",
"PAPER_SEARCH_MCP_SEMANTIC_SCHOLAR_API_KEY": ""
}
}
}
}方法 6 — Docker
docker build -t paper-search-mcp .
docker run --rm -i \
-e PAPER_SEARCH_MCP_UNPAYWALL_EMAIL=your@email.com \
-e PAPER_SEARCH_MCP_CORE_API_KEY=your_core_key \
paper-search-mcpClaude Desktop 配置:
{
"mcpServers": {
"paper-search-mcp": {
"command": "docker",
"args": ["run", "--rm", "-i", "paper-search-mcp"],
"env": {
"PAPER_SEARCH_MCP_UNPAYWALL_EMAIL": "your@email.com",
"PAPER_SEARCH_MCP_CORE_API_KEY": "",
"PAPER_SEARCH_MCP_SEMANTIC_SCHOLAR_API_KEY": "",
"PAPER_SEARCH_MCP_ZENODO_ACCESS_TOKEN": "",
"PAPER_SEARCH_MCP_GOOGLE_SCHOLAR_PROXY_URL": "",
"PAPER_SEARCH_MCP_IEEE_API_KEY": "",
"PAPER_SEARCH_MCP_ACM_API_KEY": ""
}
}
}
}方法 7 — 克隆并从源码运行(开发 / 推荐用于 macOS 本地)
这是 macOS 上最可靠的方法 — 没有包装脚本,没有 realpath 问题。
# 1. Install uv (skip if already installed)
curl -LsSf https://astral.sh/uv/install.sh | sh
# 2. Clone repo
git clone https://github.com/openags/paper-search-mcp.git
cd paper-search-mcp
# 3. Verify it runs (uv auto-resolves dependencies, no manual install needed)
uv run -m paper_search_mcp.serverClaude Desktop 配置(将目录路径替换为你实际的克隆位置):
{
"mcpServers": {
"paper-search-mcp": {
"command": "uv",
"args": [
"run",
"--directory", "/path/to/paper-search-mcp",
"-m", "paper_search_mcp.server"
],
"env": {
"PAPER_SEARCH_MCP_UNPAYWALL_EMAIL": "your@email.com",
"PAPER_SEARCH_MCP_CORE_API_KEY": "",
"PAPER_SEARCH_MCP_SEMANTIC_SCHOLAR_API_KEY": "",
"PAPER_SEARCH_MCP_ZENODO_ACCESS_TOKEN": "",
"PAPER_SEARCH_MCP_GOOGLE_SCHOLAR_PROXY_URL": "",
"PAPER_SEARCH_MCP_IEEE_API_KEY": "",
"PAPER_SEARCH_MCP_ACM_API_KEY": ""
}
}
}
}例如,如果你克隆到 /Users/mac/Pengsong/paper-search-mcp:
"args": ["run", "--directory", "/Users/mac/Pengsong/paper-search-mcp", "-m", "paper_search_mcp.server"]
uv run会在首次运行时自动将依赖安装到隔离环境中 — 无需pip install或venv。
对于活跃开发,可选安装可编辑副本:
uv venv && source .venv/bin/activate # Windows: .venv\Scripts\activate
uv pip install -e ".[dev]"环境变量(.env 文件)
你可以不把密钥直接放在 JSON 配置中,而是将它们存储在用户配置文件中(启动时自动加载):
mkdir -p ~/.config/paper-search-mcp
curl -fsSL https://raw.githubusercontent.com/openags/paper-search-mcp/main/.env.example \
-o ~/.config/paper-search-mcp/.env
$EDITOR ~/.config/paper-search-mcp/.envPAPER_SEARCH_MCP_UNPAYWALL_EMAIL=your@email.com
PAPER_SEARCH_MCP_CORE_API_KEY=
PAPER_SEARCH_MCP_SEMANTIC_SCHOLAR_API_KEY=
PAPER_SEARCH_MCP_ZENODO_ACCESS_TOKEN=
PAPER_SEARCH_MCP_GOOGLE_SCHOLAR_PROXY_URL=
PAPER_SEARCH_MCP_IEEE_API_KEY=
PAPER_SEARCH_MCP_ACM_API_KEY=要使用自定义路径:export PAPER_SEARCH_MCP_ENV_FILE=/absolute/path/to/.env
不带
PAPER_SEARCH_MCP_前缀的旧变量名(如CORE_API_KEY、UNPAYWALL_EMAIL)仍受支持,以保持向后兼容。
贡献
我们欢迎贡献!以下是入门方法:
Fork 仓库: 在 GitHub 上点击 "Fork"。
克隆并设置:
git clone https://github.com/yourusername/paper-search-mcp.git cd paper-search-mcp uv venv && source .venv/bin/activate uv pip install -e ".[dev]"进行更改:
在
academic_platforms/中添加新平台。更新
tests/中的测试。
提交 Pull Request: 推送更改并在 GitHub 上创建 PR。
演示
待办事项
计划中的学术平台
[√] arXiv
[√] PubMed
[√] bioRxiv
[√] medRxiv
[√] Google Scholar
[√] IACR ePrint Archive
[√] Semantic Scholar
[√] Crossref
[√] PubMed Central (PMC)
[√] CORE
[√] Europe PMC
[√] Sci-Hub 警告和启用文档
开发任务
[√] 修复 Async 搜索错误,确保可靠的快速 MCP 事件
[√] 端到端完整流水线测试脚本(搜索、解析、下载)
[√] 建立两层联邦架构(第 1 层工具:
search_papers)[√] 确保跨元数据字段和摘要回退的全面 DOI 提取
引文图和论文关系上下文功能
[√] 扩展全栈 OpenAlex 提供程序
优先的免费和开放来源
[√] PubMed Central (PMC)
[√] CORE
[√] OpenAlex
[√] Europe PMC
[√] OpenAIRE
[√] dblp
[√] CiteSeerX
[√] DOAJ
[√] BASE
[√] Zenodo
[√] HAL
[√] SSRN(发现 + 尽力而为的全文)
[√] Unpaywall(独立 DOI 搜索来源)
可选和非核心集成
ResearchGate
JSTOR
ScienceDirect
Springer Link
[√] IEEE Xplore(可选骨架 — 使用
IEEE_API_KEY激活)[√] ACM Digital Library(可选骨架 — 使用
ACM_API_KEY激活)Web of Science
Scopus
Star 历史
许可证
本项目根据 MIT 许可证授权。详情请参阅 LICENSE 文件。
祝您使用 paper-search-mcp 研究愉快!如果您遇到问题,请打开一个 GitHub issue。
Available Tools
57 toolsdownload_arxivA
Download PDF of an arXiv paper.
Args: paper_id: arXiv paper ID (e.g., '2106.12345'). save_path: Directory to save the PDF (default: './downloads'). Returns: Path to the downloaded PDF file.
Inputs: paper_id (required), save_path. Returns: result
download_baseB
Download PDF for a paper from BASE.
Args: paper_id: BASE paper identifier. save_path: Directory to save the PDF (default: './downloads'). Returns: str: Path to downloaded PDF.
Inputs: paper_id (required), save_path. Returns: result
download_biorxivA
Download PDF of a bioRxiv paper.
Args: paper_id: bioRxiv DOI. save_path: Directory to save the PDF (default: './downloads'). Returns: Path to the downloaded PDF file.
Inputs: paper_id (required), save_path. Returns: result
download_citeseerxA
Download PDF for a paper from CiteSeerX.
Args: paper_id: CiteSeerX paper identifier. save_path: Directory to save the PDF (default: './downloads'). Returns: str: Path to downloaded PDF or error message.
Inputs: paper_id (required), save_path. Returns: result
download_crossrefA
Attempt to download PDF of a CrossRef paper.
Args: paper_id: CrossRef DOI (e.g., '10.1038/nature12373'). save_path: Directory to save the PDF (default: './downloads'). Returns: str: Message indicating that direct PDF download is not supported.
Note: CrossRef is a citation database and doesn't provide direct PDF downloads. Use the DOI to access the paper through the publisher's website.
Inputs: paper_id (required), save_path. Returns: result
download_dblpC
Download PDF for a paper from dblp.
Note: dblp doesn't provide direct PDF access. This function returns an informative message.
Args: paper_id: dblp paper identifier. save_path: Directory to save the PDF (default: './downloads'). Returns: str: Message indicating that direct PDF download is not supported.
Inputs: paper_id (required), save_path. Returns: result
download_doajA
Download PDF for a paper from DOAJ.
Args: paper_id: DOAJ paper identifier. save_path: Directory to save the PDF (default: './downloads'). Returns: str: Path to downloaded PDF.
Inputs: paper_id (required), save_path. Returns: result
download_halB
Download PDF for a paper from HAL.
Args: paper_id: HAL paper identifier. save_path: Directory to save the PDF (default: './downloads'). Returns: str: Path to downloaded PDF.
Inputs: paper_id (required), save_path. Returns: result
download_iacrA
Download PDF of an IACR ePrint paper.
Args: paper_id: IACR paper ID (e.g., '2009/101'). save_path: Directory to save the PDF (default: './downloads'). Returns: Path to the downloaded PDF file.
Inputs: paper_id (required), save_path. Returns: result
download_medrxivA
Download PDF of a medRxiv paper.
Args: paper_id: medRxiv DOI. save_path: Directory to save the PDF (default: './downloads'). Returns: Path to the downloaded PDF file.
Inputs: paper_id (required), save_path. Returns: result
download_openaireA
Download PDF for a paper from OpenAIRE.
Args: paper_id: OpenAIRE paper identifier. save_path: Directory to save the PDF (default: './downloads'). Returns: str: Path to downloaded PDF or error message.
Inputs: paper_id (required), save_path. Returns: result
download_openalexC
Download PDF for a paper from OpenAlex.
Args: paper_id: OpenAlex paper ID. save_path: Directory to save the PDF (default: './downloads'). Returns: str: Error message, typically OpenAlex relies on extracted pdf_url instead of direct downloads.
Inputs: paper_id (required), save_path. Returns: result
download_pubmedB
Attempt to download PDF of a PubMed paper.
Args: paper_id: PubMed ID (PMID). save_path: Directory to save the PDF (default: './downloads'). Returns: str: Message indicating that direct PDF download is not supported.
Inputs: paper_id (required), save_path. Returns: result
download_scihubA
Download paper PDF via Sci-Hub (optional fallback connector).
Args: identifier: DOI, title, PMID, or paper URL. save_path: Directory to save the PDF. base_url: Sci-Hub mirror URL. Returns: Downloaded PDF path on success; error message on failure.
Inputs: identifier (required), save_path, base_url. Returns: result
download_semanticA
Download PDF of a Semantic Scholar paper.
Args: paper_id: Semantic Scholar paper ID, Paper identifier in one of the following formats: - Semantic Scholar ID (e.g., "649def34f8be52c8b66281af98ae884c09aef38b") - DOI: (e.g., "DOI:10.18653/v1/N18-3011") - ARXIV: (e.g., "ARXIV:2106.15928") - MAG: (e.g., "MAG:112218234") - ACL: (e.g., "ACL:W12-3903") - PMID: (e.g., "PMID:19872477") - PMCID: (e.g., "PMCID:2323736") - URL: (e.g., "URL:https://arxiv.org/abs/2106.15928v1") save_path: Directory to save the PDF (default: './downloads'). Returns: Path to the downloaded PDF file.
Inputs: paper_id (required), save_path. Returns: result
download_ssrnC
Download PDF for a paper from SSRN.
Note: SSRN connector is metadata-only and download is not supported.
Args: paper_id: SSRN paper identifier. save_path: Directory to save the PDF (unused). Returns: str: Error message from metadata-only SSRN connector.
Inputs: paper_id (required), save_path. Returns: result
download_with_fallbackA
Try source-native download, OA repositories, Unpaywall, then optional Sci-Hub.
Args: source: Source name (arxiv, biorxiv, medrxiv, iacr, semantic, crossref, pubmed, pmc, core, europepmc, citeseerx, doaj, base, zenodo, hal, ssrn). paper_id: Source-native paper identifier. doi: Optional DOI used for repository/unpaywall/Sci-Hub fallback. title: Optional title used for repository/Sci-Hub fallback when DOI is unavailable. save_path: Directory to save downloaded files. use_scihub: Whether to fallback to Sci-Hub after OA attempts fail. scihub_base_url: Sci-Hub mirror URL for fallback. Returns: Download path on success or explanatory error message.
Inputs: source (required), paper_id (required), doi, title, +3 more. Returns: result
download_zenodoA
Download PDF for a paper from Zenodo.
Args: paper_id: Zenodo paper identifier. save_path: Directory to save the PDF (default: './downloads'). Returns: str: Path to downloaded PDF.
Inputs: paper_id (required), save_path. Returns: result
get_crossref_paper_by_doiA
Get a specific paper from CrossRef by its DOI.
Args: doi: Digital Object Identifier (e.g., '10.1038/nature12373'). Returns: Paper metadata in dictionary format, or empty dict if not found.
Example: get_crossref_paper_by_doi("10.1038/nature12373")
Inputs: doi (required). Returns: result
read_arxiv_paperA
Read and extract text content from an arXiv paper PDF.
Args: paper_id: arXiv paper ID (e.g., '2106.12345'). save_path: Directory where the PDF is/will be saved (default: './downloads'). Returns: str: The extracted text content of the paper.
Inputs: paper_id (required), save_path. Returns: result
read_base_paperB
Read and extract text content from a BASE paper.
Args: paper_id: BASE paper identifier. save_path: Directory where the PDF is/will be saved (default: './downloads'). Returns: str: Extracted text content.
Inputs: paper_id (required), save_path. Returns: result
read_biorxiv_paperA
Read and extract text content from a bioRxiv paper PDF.
Args: paper_id: bioRxiv DOI. save_path: Directory where the PDF is/will be saved (default: './downloads'). Returns: str: The extracted text content of the paper.
Inputs: paper_id (required), save_path. Returns: result
read_citeseerx_paperA
Read and extract text content from a CiteSeerX paper.
Args: paper_id: CiteSeerX paper identifier. save_path: Directory where the PDF is/will be saved (default: './downloads'). Returns: str: Extracted text or fallback abstract/error message.
Inputs: paper_id (required), save_path. Returns: result
read_crossref_paperA
Attempt to read and extract text content from a CrossRef paper.
Args: paper_id: CrossRef DOI (e.g., '10.1038/nature12373'). save_path: Directory where the PDF is/will be saved (default: './downloads'). Returns: str: Message indicating that direct paper reading is not supported.
Note: CrossRef is a citation database and doesn't provide direct paper content. Use the DOI to access the paper through the publisher's website.
Inputs: paper_id (required), save_path. Returns: result
read_dblp_paperA
Attempt to read and extract text content from a dblp paper.
Note: dblp doesn't provide direct paper content access. This function returns an informative message.
Args: paper_id: dblp paper identifier. save_path: Directory where the PDF would be saved (unused). Returns: str: Message indicating that direct paper reading is not supported.
Inputs: paper_id (required), save_path. Returns: result
read_doaj_paperA
Read and extract text content from a DOAJ paper.
Args: paper_id: DOAJ paper identifier. save_path: Directory where the PDF is/will be saved (default: './downloads'). Returns: str: Extracted text content.
Inputs: paper_id (required), save_path. Returns: result
read_hal_paperA
Read and extract text content from a HAL paper.
Args: paper_id: HAL paper identifier. save_path: Directory where the PDF is/will be saved (default: './downloads'). Returns: str: Extracted text content.
Inputs: paper_id (required), save_path. Returns: result
read_iacr_paperA
Read and extract text content from an IACR ePrint paper PDF.
Args: paper_id: IACR paper ID (e.g., '2009/101'). save_path: Directory where the PDF is/will be saved (default: './downloads'). Returns: str: The extracted text content of the paper.
Inputs: paper_id (required), save_path. Returns: result
read_medrxiv_paperA
Read and extract text content from a medRxiv paper PDF.
Args: paper_id: medRxiv DOI. save_path: Directory where the PDF is/will be saved (default: './downloads'). Returns: str: The extracted text content of the paper.
Inputs: paper_id (required), save_path. Returns: result
read_openaire_paperA
Attempt to read and extract text content from an OpenAIRE paper.
Args: paper_id: OpenAIRE paper identifier. save_path: Directory where the PDF is/will be saved (default: './downloads'). Returns: str: Extracted text or error message.
Inputs: paper_id (required), save_path. Returns: result
read_openalex_paperC
Attempt to read and extract text content from an OpenAlex paper.
Args: paper_id: OpenAlex paper ID. save_path: Directory where the PDF is/will be saved (default: './downloads'). Returns: str: Message indicating that direct paper reading is not supported natively.
Inputs: paper_id (required), save_path. Returns: result
read_pubmed_paperD
Read and extract text content from a PubMed paper.
Args: paper_id: PubMed ID (PMID). save_path: Directory where the PDF would be saved (unused). Returns: str: Message indicating that direct paper reading is not supported.
Inputs: paper_id (required), save_path. Returns: result
read_semantic_paperA
Read and extract text content from a Semantic Scholar paper.
Args: paper_id: Semantic Scholar paper ID, Paper identifier in one of the following formats: - Semantic Scholar ID (e.g., "649def34f8be52c8b66281af98ae884c09aef38b") - DOI: (e.g., "DOI:10.18653/v1/N18-3011") - ARXIV: (e.g., "ARXIV:2106.15928") - MAG: (e.g., "MAG:112218234") - ACL: (e.g., "ACL:W12-3903") - PMID: (e.g., "PMID:19872477") - PMCID: (e.g., "PMCID:2323736") - URL: (e.g., "URL:https://arxiv.org/abs/2106.15928v1") save_path: Directory where the PDF is/will be saved (default: './downloads'). Returns: str: The extracted text content of the paper.
Inputs: paper_id (required), save_path. Returns: result
read_ssrn_paperB
Read paper content from SSRN.
Note: SSRN connector is metadata-only and read is not supported.
Args: paper_id: SSRN paper identifier. save_path: Directory where the PDF is/will be saved (unused). Returns: str: Error message from metadata-only SSRN connector.
Inputs: paper_id (required), save_path. Returns: result
read_zenodo_paperA
Read and extract text content from a Zenodo paper.
Args: paper_id: Zenodo paper identifier. save_path: Directory where the PDF is/will be saved (default: './downloads'). Returns: str: Extracted text content.
Inputs: paper_id (required), save_path. Returns: result
search_arxivB
Search academic papers from arXiv.
Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results. Returns: result
search_baseA
Search academic papers from BASE (Bielefeld Academic Search Engine).
Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results. Returns: result
search_biorxivA
Search academic papers from bioRxiv.
Note: bioRxiv API filters by category name within the last 30 days, not full-text keyword search. Use a category keyword such as 'bioinformatics', 'neuroscience', 'cell biology', etc.
Args: query: Category name to filter by (e.g., 'bioinformatics', 'neuroscience'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results. Returns: result
search_citeseerxB
Search academic papers from CiteSeerX digital library.
Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results. Returns: result
search_coreB
Search academic papers from CORE.
Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results. Returns: result
search_crossrefA
Search academic papers from CrossRef database.
CrossRef is a scholarly infrastructure organization that provides persistent identifiers (DOIs) for scholarly content and metadata. It's one of the largest citation databases covering millions of academic papers, journals, books, and other scholarly content.
Args: query: Search query string (e.g., 'machine learning', 'climate change'). max_results: Maximum number of papers to return (default: 10, max: 1000). filter: CrossRef filter string (e.g., 'has-full-text:true,from-pub-date:2020'). sort: Sort field ('relevance', 'published', 'updated', 'deposited', etc.). order: Sort order ('asc' or 'desc'). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results, filter, sort, +1 more. Returns: result
search_dblpA
Search academic papers from dblp computer science bibliography.
Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results. Returns: result
search_doajA
Search academic papers from DOAJ (Directory of Open Access Journals).
Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results. Returns: result
search_europepmcA
Search academic papers from Europe PMC.
Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results. Returns: result
search_google_scholarB
Search academic papers from Google Scholar.
Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results. Returns: result
search_halB
Search academic papers from HAL open archive.
Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results. Returns: result
search_iacrA
Search academic papers from IACR ePrint Archive.
Args: query: Search query string (e.g., 'cryptography', 'secret sharing'). max_results: Maximum number of papers to return (default: 10). fetch_details: Whether to fetch detailed information for each paper (default: True). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results, fetch_details. Returns: result
search_medrxivA
Search academic papers from medRxiv.
Note: medRxiv API filters by category name within the last 30 days, not full-text keyword search. Use a category keyword such as 'infectious_diseases', 'cardiovascular_medicine', 'oncology', etc.
Args: query: Category name to filter by (e.g., 'infectious_diseases', 'oncology'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results. Returns: result
search_openaireA
Search academic papers from OpenAIRE European Open Access infrastructure.
Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results. Returns: result
search_openalexA
Search academic papers from OpenAlex.
Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results. Returns: result
search_papersA
Unified top-level search across all configured academic platforms.
Args: query: Search query string. max_results_per_source: Max results to fetch from each selected source. sources: Comma-separated source names or 'all'. Available: arxiv,pubmed,biorxiv,medrxiv,google_scholar,iacr,semantic,crossref,openalex,pmc,core,europepmc,dblp,openaire,citeseerx,doaj,base,zenodo,hal,ssrn,unpaywall year: Optional year filter for Semantic Scholar only. Returns: Aggregated dictionary with per-source stats, errors, and deduplicated papers.
Inputs: query (required), max_results_per_source, sources, year. Returns: result
search_pmcB
Search academic papers from PubMed Central (PMC).
Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results. Returns: result
search_pubmedB
Search academic papers from PubMed.
Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results. Returns: result
search_semanticA
Search academic papers from Semantic Scholar.
Args: query: Search query string (e.g., 'machine learning'). year: Optional year filter (e.g., '2019', '2016-2020', '2010-', '-2015'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Inputs: query (required), year, max_results. Returns: result
search_ssrnA
Search metadata records from SSRN.
Note: SSRN connector is metadata-only and does not support direct PDF download.
Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results. Returns: result
search_unpaywallA
Lookup a DOI via Unpaywall and return OA metadata.
Unpaywall is DOI-centric and does not support generic keyword search.
This tool extracts the first DOI from query and returns at most one record.
Args: query: DOI string or text containing a DOI. max_results: Kept for API consistency; Unpaywall returns max 1 record. Returns: List with one paper metadata dict when DOI is resolvable, else empty list.
Inputs: query (required), max_results. Returns: result
search_zenodoB
Search academic papers from Zenodo open repository.
Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Inputs: query (required), max_results. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 57 tools
The tools are highly ambiguous due to extensive overlap across sources; for example, download_arxiv and download_semantic both download PDFs, and search_arxiv and search_semantic both search papers, making it difficult for an agent to choose the right tool without deep knowledge of each source. The descriptions clarify the source but not the functional distinction, leading to potential misselection when the agent doesn't care about the specific source.
Tool names follow a perfectly consistent verb_noun pattern throughout, with all tools using snake_case and clear prefixes like download_, read_, search_, and get_. This predictability makes it easy for an agent to understand the action and target, such as download_arxiv_paper or search_crossref.
With 57 tools, the count is extremely high for a paper search server, far exceeding the typical well-scoped range of 3-15 tools. This creates a bloated and overwhelming interface that is difficult for an agent to navigate efficiently, as many tools are redundant across sources rather than adding unique functionality.
The tool set is highly complete for the domain of paper search and retrieval, covering download, read, search, and metadata retrieval across numerous academic sources. There are no obvious gaps; the tools provide full lifecycle coverage from discovery to content extraction, including a unified search tool for convenience.
Maintenance
Related MCP Connectors
Academic research MCP server for paper search, citation checks, graphs, and deep research.
Zotero MCP server for Claude and ChatGPT: search, citations, safe writes, PDF passages and pages.
Search and download academic papers from arXiv, PubMed, bioRxiv, medRxiv, Google Scholar, Semantic…
Related MCP Servers
- AlicenseBqualityDmaintenanceAn MCP server that allows Claude AI to search, explore, and compare arXiv papers efficiently through a custom-built local server.419MIT
- AlicenseNot gradedqualityDmaintenanceA MCP server for academic literature retrieval, aggregating multiple data sources like arXiv, Crossref, OpenAlex, PubMed, and Semantic Scholar to provide search, details, citations, trends, and recommendations.4MIT
- FlicenseAqualityDmaintenanceA local MCP server for searching and reading arXiv papers, enabling paper search, retrieval, and summarization through Claude.6-
- AlicenseNot gradedqualityDmaintenanceMCP server for searching, downloading, and reading academic papers from multiple sources such as arXiv, Google Scholar, and Elsevier.5MIT
Appeared in Searches
- Official Consensus.app MCP server for AI-powered research and academic search
- A server for accessing full-text research articles via DOI
- A server for finding academic papers to perform sentiment analysis and develop a consumer-facing voice chatbot
- A tool for finding relevant academic publications and open-source projects on GitHub
- A server for finding academic and scholarly articles