原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Datacite MCP Server

作者:cyanheads版本 0.2.1i★ –i电脑或云端
注册名称io.github.cyanheads/datacite-mcp-server

安装

概览

作者提供的说明(英文原文)

Search DataCite datasets and software, fetch DOI metadata, trace relations, format citations.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

  • 基础检查:3 项中通过 3 项
  • 在作者的服务器上运行:你向它提出的内容会经过他们的服务器。
  • 可以做 6 件事(工具) datacite_search_works, datacite_get_work, datacite_trace_relations, datacite_search_repositories …
  • 需要你自己填写: DATACITE_CLAMP_LIMITS, MCP_LOG_LEVEL, DATACITE_CONTACT_EMAIL, DATACITE_MAX_REQUESTS_PER_5MIN

你需要

  • 在云端运行无需安装任何东西,通过互联网连接
  • npm已安装 Node.js(用于 npx 命令)

你用的是哪个应用?

在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。

适用于网页版、桌面版和手机版 Claude:

  1. 打开 Settings → Connectors
  2. 点击 Add custom connector
  3. 粘贴下面的地址,然后点击 Add
  4. 如果要求登录,请登录作者的服务
SettingsConnectors1+ Add2https://…3
https://datacite.caseyjhand.com/mcp

或者在你的电脑上运行

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "datacite": {
      "command": "npx",
      "args": [
        "-y",
        "@cyanheads/datacite-mcp-server"
      ],
      "env": {
        "DATACITE_CLAMP_LIMITS": "your-value",
        "MCP_LOG_LEVEL": "your-value",
        "DATACITE_CONTACT_EMAIL": "your-value",
        "DATACITE_MAX_REQUESTS_PER_5MIN": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add --transport http datacite https://datacite.caseyjhand.com/mcp

或者在你的电脑上运行

claude mcp add datacite --env DATACITE_CLAMP_LIMITS=your-value --env MCP_LOG_LEVEL=your-value --env DATACITE_CONTACT_EMAIL=your-value --env DATACITE_MAX_REQUESTS_PER_5MIN=your-value -- npx -y @cyanheads/datacite-mcp-server

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "datacite": {
      "url": "https://datacite.caseyjhand.com/mcp"
    }
  }
}

或者在你的电脑上运行

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "datacite": {
      "command": "npx",
      "args": [
        "-y",
        "@cyanheads/datacite-mcp-server"
      ],
      "env": {
        "DATACITE_CLAMP_LIMITS": "your-value",
        "MCP_LOG_LEVEL": "your-value",
        "DATACITE_CONTACT_EMAIL": "your-value",
        "DATACITE_MAX_REQUESTS_PER_5MIN": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "datacite": {
      "type": "http",
      "url": "https://datacite.caseyjhand.com/mcp"
    }
  }
}

或者在你的电脑上运行

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "datacite": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@cyanheads/datacite-mcp-server"
      ],
      "env": {
        "DATACITE_CLAMP_LIMITS": "your-value",
        "MCP_LOG_LEVEL": "your-value",
        "DATACITE_CONTACT_EMAIL": "your-value",
        "DATACITE_MAX_REQUESTS_PER_5MIN": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

ChatGPT 只能连接互联网上的服务器:

  1. 打开网页版 ChatGPT → Settings → Connectors (Apps)
  2. 点击 Create 或 Add(部分套餐需要先在 Advanced 中开启 Developer mode)
  3. 粘贴下面的地址,起个名字,然后保存
  4. 如果要求登录,请登录作者的服务
SettingsConnectors1+ Create2https://…3
https://datacite.caseyjhand.com/mcp

菜单名称可能因套餐和版本不同而略有差异。

你的选择通过 Cookie 保存在这台设备上,无需账户。

需要你填写的值

  • DATACITE_CLAMP_LIMITS env
    true applies at most 1,000 search rows or 100 graph nodes with a notice; false advertises and enforces strict maxima.
  • MCP_LOG_LEVEL env
    Sets the minimum log level for output (e.g., 'debug', 'info', 'warn').
  • DATACITE_CONTACT_EMAIL env
    Contact email sent in the User-Agent as mailto: (never a URL parameter). Moves requests to DataCite's identified tier (1,000 per 5 minutes per IP instead of 500).
  • DATACITE_MAX_REQUESTS_PER_5MIN env
    Request budget per 5-minute window, 50-1000. Default 800 with a contact email, 400 without; divide it across replicas sharing one egress IP.

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

它能做什么

工具名称和描述与服务器在 2026年11月6日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。

  • datacite_search_works

    Search DataCite DOI metadata for datasets, software, samples, workflows, and other research outputs. Combine plain words (`text`) or OpenSearch query syntax (`query`) with filters for resource type, creator (ORCID iD or name), affiliation (ROR ID or name), affiliation country, fu

  • datacite_get_work

    Fetch the full deposited DataCite metadata for one DOI: titles, creators and contributors with ORCID iDs and ROR affiliations, publisher, dates, version, subjects, descriptions, funding, geolocations, rights, sizes and formats, related identifiers with their relation types, repos

  • datacite_trace_relations

    Map the relation graph around one DOI — versions, parts, supplements, derivations, documentation, citations, references, and every other DataCite relation type — as nodes and directed edges that keep the relationType exactly as asserted and name each edge's source: the DOI's own

  • datacite_search_repositories

    Find DataCite repository accounts by name or description text, field of science, repository type, certification (e.g. CoreTrustSeal), software platform, client type, or parent provider, or look up known repository IDs. Returns each repository's repositoryId — the value datacite_s

  • datacite_get_citation

    Render one DataCite DOI as a formatted citation in a CSL style and locale (APA in US English by default), or as a machine-readable record: CSL JSON, BibTeX, RIS, DataCite JSON or XML, Schema.org JSON-LD, Codemeta, or JATS. A style the upstream renderer does not support — an unkno

  • datacite_list_reference

    Look up the controlled vocabularies and identifier forms the other datacite_* tools accept: resource types, relation types with their inverses and groups, related-identifier types, date and contributor types, fields of science, common license ids, repository types, certificates,

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 cyanheads 验证,该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • ✓ 通过

    端点有响应

    在 131 毫秒内响应(HTTP 200)

  • – 不适用

    使用 OAuth 登录

    无需登录

  • ✓ 通过

    工具描述中没有隐藏指令

    已读取 6 个工具描述,未发现针对 AI 的隐藏指令

与“搜索与 AI 记忆”中的其他服务器比较i

  • 星标数多于此分类中其他 7277 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 7277 个服务器的 85% 更新
  • 基础检查结果等于或优于此分类中其他 7277 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Datacite MCP Server 安全吗?

它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

两种方式都可以:安装在你的电脑上,或者连接云端版本。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(0.2.1)于6天前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。

有什么可以替代它?

同一分类中有:Context7, Codebase Memory, Exa

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Context7

作者:upstash

Up-to-date docs for AI agents

电脑或云端★ 64,224MIT昨天更新
安装

Codebase Memory

作者:DeusData

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

在你的电脑上运行★ 48,148MIT21天前更新
安装

Exa

作者:exa-labs

Connect AI agents to Exa for web search, content fetching, and multi-step research.

在云端运行★ 5,213MIT上个月更新
安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

@cyanheads/datacite-mcp-server Search DataCite datasets and software, fetch DOI metadata, trace relations, format citations via MCP. STDIO or Streamable HTTP. 6 Tools

Public Hosted Server: https://datacite.caseyjhand.com/mcp


Overview

DOI metadata from DataCite for datasets, software, samples, workflows, and other research outputs that repositories deposit worldwide. Search it, open a record in full, trace a DOI's relations (versions, parts, supplements, citations), find the repositories that publish in a field, and format citations. No API key required.

Tools
ToolDescription
datacite_search_worksSearch works by plain text or query syntax plus structured filters, in ranked pages or a full cursor walk, with optional facet counts
datacite_get_workFetch the full deposited metadata for one DOI, or learn which registration agency holds a DOI DataCite doesn't
datacite_trace_relationsMap the relation graph around any DOI — versions, parts, supplements, derivations, citations — with each edge's source
datacite_search_repositoriesFind repository accounts by text, field of science, type, certificate, software, or provider, and get the repositoryId work search filters on
datacite_get_citationRender a DOI as a formatted citation in a CSL style and locale, or as BibTeX, RIS, CSL JSON, and other machine formats
datacite_list_referenceLook up the vocabularies, identifier forms, and coverage rules the other tools accept, offline

Capability reference

datacite_search_works tool
  • text (literal words, with angle brackets removed; nonblank text that leaves no searchable clause fails as invalid_text) or query (OpenSearch query syntax), ANDed with filters: resource_types, creator (ORCID iD or name), affiliation (ROR ID or name), affiliation_country, funder (ROR ID, Crossref Funder ID, or name; include_child_funders with a ROR funder), subject, fields_of_science, repository_ids, provider_ids, licenses, language, place, published_from / published_to, and min_citations; list filters take up to 10 values, any of which match
  • Positive integer limit (default 20), applied at most 1,000 with a requested/applied notice; ranked pages reach the first 10,000 matches under sort (relevance, newest, oldest, recently_updated, most_cited, most_viewed, most_downloaded; default relevance with text or query, else newest), while cursor: "*" walks the whole result set in registration order through nextCursor and takes neither page nor sort. A ranked ceiling stop is distinguished from the last page
  • affiliation_country accepts current and formerly assigned ISO alpha-2 codes plus XK, in any case. UK maps to GB with a notice; unassigned codes fail as invalid_filter before searching
  • Crossref Funder IDs resolve through one exact ROR FundRef mapping before searching funded-by; an unavailable, incomplete, or ambiguous mapping keeps literal identifier matching and discloses reduced coverage. The cached, paced lookup takes at most five seconds without retry. A cursor walk keeps its initial resolved or literal filter on every continuation without another ROR lookup, including across server restarts. include_child_funders still requires an explicitly supplied ROR
  • License ids are trimmed and lowercased, preserving internal spaces (cc0 1.0 differs from cc0-1.0); reuse the licenses facet ids exactly. query also supports deposition timestamps, e.g. created:[2026-10-16 TO *], updated, and registered
  • include_facets adds top counts for resource types, years, repositories, providers, affiliations, fields of science, and licenses (2–8 s slower); every response reports totalCount, effectiveQuery, sortApplied, and appliedFilters

datacite_get_work tool
  • One doi, in any case: bare, with a doi: or info:doi/ prefix, as a doi.org URL, or %2F-encoded
  • Titles, creators and contributors with ORCID iDs and ROR affiliations, dates, subjects, descriptions, funding, geolocations, rights, related identifiers and items, repository and provider, and counts (citations, references, versions, parts, views, downloads); long lists are capped and their full sizes reported in truncatedLists and relatedIdentifierCounts
  • Page one capped list with a zero-based offset (default 0): creators, contributors, relatedIdentifiers, subjects, and fundingReferences return up to 100 entries, relatedItems 25, and geoLocations 50. Offsets index valid mapped entries in deposit order. listPage reports list, offset, total, and nextOffset while entries remain; other metadata keeps its normal caps. Default truncation notices give exact continuation inputs. An offset requires a list; past-end pages are empty
  • Titles and search snippets are plain text, with recognized formatting tags removed and entities decoded once before snippet truncation, including all semicolon-terminated WHATWG named references such as α and β. Structured descriptions keep their deposited text; rendered descriptions preserve paragraph and line boundaries
  • Geolocations preserve points, boxes, ordered polygon vertices, and optional polygon interior points. Incomplete polygons are omitted with a notice; valid sibling geometry remains
  • A DOI DataCite holds no public record for returns found: false with missReason (other_agency, does_not_exist, not_public, unclassified), the registrationAgency when known, and guidance

datacite_trace_relations tool
  • Any agency's doi: a DataCite dataset or software DOI, or a journal article's DOI to find the DataCite data and software it cites or that cite, supplement, or derive from it
  • depth 1 (default) or 2 — the second hop expands at most 10 DataCite neighbours and runs only when the first hop leaves max_nodes room; positive integer max_nodes (default 50, root included), applied at most 100 with a notice, fills with own-metadata targets, then records pointing at the root, then Event Data endpoints, then the second hop; relation_types keeps only the listed relation types, read from the traced DOI's side (omitted: all); include_event_data (default true) adds Event Data citation links
  • Edges keep relationType exactly as asserted and list their sources (metadata, reverse_metadata, event_data); coverage states how much of each source was read (up to 100 reverse records per hop, only the first 10 when those are large, and up to 100 events per call), and rootCounts carries DataCite's own counts for comparison. An absent edge is not evidence that no relationship exists
  • Reverse lookups inspect both relatedIdentifiers and identified relatedItems, verify each assertion's target and type, and merge identical edges
  • event_offset (0–9,999, absolute and zero-based) selects Event-Data-only tracing, including when set to 0: metadata edges and depth-2 expansion are skipped. Continue with coverage.eventData.nextEventOffset and the same DOI and filters. Each call reads one upstream page and stops before an eligible endpoint that cannot fit max_nodes; root-only calls explain how to raise the cap. Coverage distinguishes exhaustion, a blocked classification lookup, unavailable/skipped reads, and the upstream 10,000-result ceiling. Upstream ordering can change between calls; continuations are not snapshots

datacite_search_repositories tool
  • query text over names and descriptions, plus field_of_science, repository_types, certificates, software, client_type, and provider_id; or repository_ids alone (up to 1,000 inputs) to look up the first 25 distinct normalized ids in input order. A notice names unqueried ids; missing-id notices cover queried ids only
  • Positive integer limit (default 20), applied at most 1,000 with a requested/applied notice, with page; name-ordered rows carry the repositoryId that datacite_search_works takes in repository_ids, plus providerId, types, certificates, software, subjects, homepage, and re3data link
  • Search responses echo the composed effectiveQuery (* without query clauses), including empty pages; ID lookups report appliedFilters.repository_ids without a query echo

datacite_get_citation tool
  • format: text (default), csl_json, bibtex, ris, datacite_json, datacite_xml, schema_org, codemeta, or jats
  • For text only: style takes a CSL style id (default apa; verified ids under datacite_list_reference topic citation_styles), and one DataCite would silently render as APA fails as unsupported_style; locale takes one of the 61 CSL locales DataCite renders (en-GB, de-DE, fr-FR, …) or a bare language code that expands to its primary dialect (de → de-DE), default en-US (list: topic citation_locales)
  • text returns the citation as plain text in citation and the upstream markup in citationHtml; text payloads over 100,000 UTF-16 code units are cut without splitting a surrogate pair. Machine formats return complete payloads inline up to that cap; larger documents omit citation and return downloadUrl for the full document and totalCharacters, with truncated: true, shown: 0, and cap: 100000. A DOI DataCite doesn't hold returns found: false as in datacite_get_work; a format DataCite can't render for that DOI fails as format_unavailable
  • JATS stays verbatim. A notice reports empty name elements or a year that disagrees with its ISO date, including when the document is returned by download URL; use csl_json, bibtex, ris, or datacite_json for another representation

datacite_list_reference tool
  • topic: resource_types, relation_types, `identifie

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx