paper-download-mcp
paper-download-mcp
通用论文获取器 MCP:按 DOI/UT 标识探测 provider、下载到短生命周期暂存区、核验 PDF、清理。不连接 PostgreSQL,不接收 project/output_dir/year/publisher/filename,不管理最终存储——这些是调用项目(如 HC 集成侧)的职责。
架构(2026-07-22 收敛)
MCP (通用获取器) 调用项目集成侧
health 任务规划与项目筛选
list_providers 最终存储与资产登记
probe(identifier, hint?) 批量编排与限速
fetch(identifier, hint?) → artifact 下载审计
verify_artifact(id) 项目级状态管理
discard_artifact(id)Related MCP server: literature-agent-mcp
工具(6 个)
工具 | 说明 |
| 版本/暂存目录/provider 可用性(不回显 key) |
| 列出 provider 及状态 |
| 探测 provider 能否获取某标识 |
| 下载到暂存区,返回 artifact_id(不收 project/output_dir 等) |
| 核验暂存 PDF(存在/页数/哈希/大小) |
| 清理暂存 artifact |
fetch 返回:artifact_id / temp_path / 来源 / 字节数 / SHA-256 / 页数 / 状态 / 失败分类。
Providers
Provider | 状态 | 说明 |
| ✅ | 测试用,合成 PDF,无网络 |
| ✅ 受控启用 | Article Retrieval API;需要授权、校园网 IP 和 0600 key 文件 |
| ✅ | cloakbrowser 提取 PDF 链接并捕获浏览器下载 |
| ✅ | cloakbrowser 获取 cookie,requests 下载;订阅范围有限 |
| ✅ | 重定向后的文章 URL 从 |
| ✅ | DOI 期刊前缀映射到 PLOS PDF 地址 |
| ✅ | 文章页与 DOI 后缀构造 PDF 地址 |
| ✅ | Springer 同类页面结构与 cookie 下载 |
Elsevier key 只经 PAPER_DOWNLOAD_ELSEVIER_API_KEY_FILE 指向的 mode 0600 文件进入,不进工具参数/日志/消息。
这些 provider 的页面规则来自已有英文文献下载工作的实战记录,具体限制和证据见 docs/provider-acceptance.md。代码中的“已实现”不等于当前网络环境下每篇论文都可下载;订阅、页面变化、限流和文章下线仍会导致可解释的失败。
本项目不集成 scansci-pdf。它是独立的第三方 MCP,不属于本项目的 provider 链路。
安装与运行
cd paper-download-mcp
python -m pip install -e ".[dev,browser]"
# 测试(无网络无 DB 无 secret)
python -m pytest tests -v
# 启动 MCP (stdio)
paper-download-mcp # 或 python -m paper_download_mcp浏览器 provider 需要 cloakbrowser;Elsevier 的页数核验需要系统提供 pdfinfo(通常由 poppler-utils 提供)。
调用项目集成侧
项目侧负责候选 SQL、canonical 落盘策略、编排循环、资产表和下载审计。这个 MCP 只交付暂存 artifact 及其核验元数据。
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityBmaintenanceAn MCP server for downloading academic papers from multiple sources using intelligent routing and year-aware priority selection. It enables users to retrieve metadata and download single or batch PDFs by DOI or URL.32MIT
- FlicenseCqualityDmaintenanceExposes a local biomedical literature pipeline as MCP tools for automated research workflows. Enables literature search, open-access paper retrieval, and draft generation for biomedical and pathology domains through standard MCP clients.6
- AlicenseAqualityDmaintenanceAn MCP server that resolves paper requests (DOI, arXiv, etc.), checks a local store, fetches open-access PDFs, and returns request IDs. It integrates with acatome-extract for ingestion and provides tools for submission, status, update, and file upload.4GPL 3.0
- AlicenseAqualityAmaintenanceMCP server for downloading academic papers from DOI or title, resolving references, and generating citations. Supports batch downloads, multiple mirrors, and optional Unpaywall integration.2111MIT
Related MCP Connectors
IEEE Xplore MCP — BYOK wrapper over the IEEE Xplore Metadata Search API
MCP server for the PDFGate API. Generate PDFs, manage documents and handle e-signatures.
Unpaywall MCP — open-access lookup for scholarly papers (free, no key)
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/TIGERwu0118/paper-download-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server