Paperport

io.github.CloudCorpRecords由 GitHub 账号 CloudCorpRecords 发布v0.1.0更新于 Nov 7, 2026

Search and read arXiv papers, with local paper storage.

已验证STDIO仅桌面网页搜索与抓取文件与存储知识与记忆

概览

AI 生成的概览

搜索 arXiv 公开 API、获取论文摘要，并把下载的论文保存在本地书架，供助手列出和再次阅读。

可以做什么
  • 按查询词搜索 arXiv 论文，可限定结果数量、日期范围和分类
  • 按论文 id 获取单篇论文的摘要、作者、日期和 PDF 链接
  • 下载论文的元数据与摘要，保存为本地 markdown 文件
  • 列出本地书架中的论文，并读取已保存论文的内容
适用场景
适合让助手检索 arXiv 文献、获取摘要，并在本地保留一小批论文以便日后离线查阅，无需再次联网查询。
运行要求
以本地 stdio 进程运行，可通过 npx 使用 npm 包，或使用 Docker 镜像。需要访问公开 arXiv API 的网络连接。无需认证或 API 密钥。存储位置由环境变量 PAPERPORT_STORAGE_DIR 指定，否则使用工作目录下的 papers 目录。
安装前请注意
下载的论文以 markdown 文件保存，仅含元数据和摘要，并非转换后的 PDF 全文，因此 read_paper 返回的是摘要文件而非论文正文。下载会向本地存储目录写入文件。查询词和论文 id 会发送到公开的 arXiv API。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Paperport，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

paperport

paperport is a small desk for arXiv work. It searches the public arXiv API, pulls back titles, authors, dates, categories and abstracts in a tidy shape, fetches the abstract for a single paper when you have its id, and keeps a local shelf of papers you have downloaded so you can list and re-read them later without going back to the network.

Install

bash
npx @reneturcios/paperport search "small language models"

Or run the container image:

bash
docker run -i ghcr.io/cloudcorprecords/paperport

The container defaults to the MCP server (see below). Pass CLI arguments to use it as a CLI instead.

CLI

Commands print JSON, except read, which prints the stored paper.

bash
# Search, with optional filterspaperport search "attention patterns" --max-results 5 \  --date-from 2024-01-01 --date-to 2024-12-31 --categories cs.CL,cs.LG
# One paper's abstractpaperport abstract 2401.12345
# Store a paper locally, then list and read the shelfpaperport download 2401.12345paperport listpaperport read 2401.12345
paperport --version

Downloaded papers are stored as <paper_id>.md files in the storage directory: the PAPERPORT_STORAGE_DIR environment variable when set, otherwise ./papers.

Exit codes: 0 on success, 1 when a paper cannot be found, fetched or read, 2 for usage errors.

MCP server

One bin serves both faces. The mcp subcommand starts a stdio MCP server:

bash
npx -y @reneturcios/paperport mcp

MCP client configuration:

json
{  "mcpServers": {    "paperport": {      "command": "npx",      "args": ["-y", "@reneturcios/paperport", "mcp"]    }  }}

Tools

ToolInputWhat it returns
search_papersquery (string, required), max_results (integer, optional), date_from / date_to (strings, optional, YYYY-MM-DD), categories (array of strings, optional)A list of papers: id, title, summary, authors, published, categories, and pdf_url.
get_abstractpaper_id (string, required)The paper's paper_id, title, abstract, authors, published, and pdf_url.
download_paperpaper_id (string, required)Stores the paper locally (see the gap note below) and returns its paper_id, title, storage path, and pdf_url.
list_papers(no input)The papers on the local shelf: each stored file's paper_id and path.
read_paperpaper_id (string, required)The stored paper's paper_id and full text content. Errors when the paper has not been downloaded.

Paper ids may be given bare (2401.12345), with a version suffix (2401.12345v2), or as a full arxiv.org/abs/... URL; they are normalised before use.

Known gap: downloaded papers are abstract files, not converted PDFs

The original tool this rebuilds converts each downloaded paper's PDF to markdown. paperport does not do that conversion: download_paper stores the paper's metadata and abstract — title, authors, categories, dates, and links to the abstract page and the PDF — as a markdown file, and read_paper returns that file. The full text of the paper is only available through the linked PDF. This is a deliberate, documented limitation of this version, not a silent one.

Development

bash
npm installnpm run build   # tsc -> dist/npm test        # node test runner over test/*.test.ts, no networknpm run dev     # run the CLI from source via tsx

License

MIT — see LICENSE.

来源：README.md，提交 461e5bc

工具

5

search_papers

Search arXiv papers by query.

输入参数query必填date_todate_fromcategoriesmax_results

get_abstract

Get the abstract for an arXiv paper.

输入参数paper_id必填

download_paper

Download an arXiv paper and store it locally.

输入参数paper_id必填

list_papers

List papers stored locally.

无需输入参数。

read_paper

Read a locally stored arXiv paper.

输入参数paper_id必填

版本历史

1
  1. v0.1.0最新Oct 31, 2026

评分

已满足适用检查项的 90%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分
  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。

  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分