Orcid Mcp Server

io.github.cyanheads由 GitHub 帳號 cyanheads 發布v0.4.1更新於 Nov 16, 2026

Researcher profiles, works, affiliations, funding, and peer reviews from the ORCID registry.

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取知識與記憶

概覽

AI 產生的概覽

唯讀存取 ORCID 研究者記錄:個人資料、著作、任職、資助、同儕審查,以及作者姓名消歧。

可以做什麼
  • 依姓名、機構、關鍵字、ROR ID、DOI、PMID 或補助編號檢索 ORCID 登錄庫,並把模糊的作者姓名解析為排序後的 ORCID iD 候選
  • 取得研究者公開資料,包含姓名、簡介、關鍵字、外部識別碼、電子郵件、國家,以及可選的記錄歷程
  • 依著作類型與發表年份篩選著作清單,再依 put-code 取得摘要、貢獻者與引用中繼資料
  • 取得任職經歷、資助摘要與獎項詳情、同儕審查活動,以及研究資源分配
  • 透過 orcid:// 資源讀取穩定的資料與著作脈絡,DOI 與 PMID 已格式化為可串接 Crossref 或 PubMed 的形式
適用情境
適合建立研究者檔案、確認某位作者對應的 ORCID iD、查核論文、資助或審查活動,或把學術記錄與其他以識別碼為基礎的服務串接時使用。
執行需求
可使用託管的 HTTP 端點,或透過 npx 在本機執行(需 Node.js)。ORCID 公開 API 不需 API 金鑰。選用環境變數可設定傳輸方式、HTTP 主機/連接埠/路徑、日誌等級、驗證模式,以及 ORCID API 基礎網址覆寫。
安裝前請注意
僅讀取公開資料,不會寫入 ORCID。只回傳公開可見欄位,空白區段可能是被隱藏而非不存在。記錄文字由研究者與資料提交系統撰寫,應視為資料而非指令。較大的分頁與批次著作詳情請求可能產生非常大的回應。公開 API 的使用須遵守 ORCID 關於非商業用途的條款。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Orcid Mcp Server,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.cyanheads%2Forcid-mcp-server/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "orcid": {
      "type": "http",
      "url": "https://orcid.caseyjhand.com/mcp"
    }
  }
}

README

@cyanheads/orcid-mcp-server

Search and retrieve researcher profiles, works, affiliations, funding, and peer review records from the ORCID registry via MCP. STDIO or Streamable HTTP.

9 Tools • 2 Resources

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


Overview

Researcher identity data from the ORCID registry. Search and disambiguate authors, build a researcher dossier from profile, works, affiliations, funding, and peer review records, and chain external identifiers to Crossref, PubMed, or arXiv.

Tools

ToolDescription
orcid_search_researchersSearch the ORCID registry using structured field params (name, affiliation, keyword, ROR ID, DOI, PMID, grant number)
orcid_get_profileFetch a researcher's public profile — name, other names, biography, keywords, researcher URLs, external identifiers, public emails with verified flags, countries, and on request the record's history
orcid_get_worksRetrieve works (publications, datasets, software, preprints) for a researcher, filtered by work type and publication year, paginated
orcid_get_work_detailAccept up to 1,000 put-codes, fetch the first 100 distinct works, and return deferred codes for continuation
orcid_get_affiliationsFetch affiliation records: employment, education, memberships, and more
orcid_get_fundingList grouped funding summaries or select one award's deposited description, amount, funding subtype, contributors, and source
orcid_get_peer_reviewsFetch peer review activity: convening organizations, reviewer role, review type
orcid_get_research_resourcesList research resources — compute allocations, equipment access, lab facilities
orcid_resolve_researcherDisambiguate an ambiguous author name to a ranked list of verified ORCID iD candidates, each with its other names; a notice flags a partial ranking or an anchor-only answer

Resources

ResourceDescription
orcid://researcher/{orcid_id}/profileResearcher profile (person section) — name, other names, bio, keywords, external IDs
orcid://researcher/{orcid_id}/worksWorks list for a researcher — the first 25 plus the total count

All resource data is also reachable via tools. Use resources when injecting stable researcher context into a prompt; use tools when filtering or processing results is needed.

The server also publishes an agent skill, orcid-guide (skill://orcid-guide/SKILL.md, source in skills/orcid-guide/): identity-confirmation gates, identifier chains between the tools, and raw Solr field syntax.

Capability reference

orcid_search_researchers tool

  • Structured params — given_name, family_name, affiliation, keyword, ror_id, doi, pmid, grant_number — AND together automatically; query adds raw Solr syntax — sent as written when it is the only field, otherwise ANDed as one parenthesized group so a top-level OR keeps its alternatives (an exclusion-only query such as -keyword:x is ANDed ungrouped, since ORCID matches nothing for a group of only exclusions)
  • At least one param must be non-blank — an empty or whitespace-only search is rejected rather than run against the whole registry
  • given_name phrase-matches, except that a value of only initials (J., J. A.) matches given names starting with each letter
  • doi and pmid map to doi-self / pmid-self field queries — finds researchers who linked that specific work to their ORCID record. URL and label forms (https://doi.org/…, doi:…, https://pubmed.ncbi.nlm.nih.gov/…/, PMID:…) are accepted and reduced to the bare identifier. A DOI anchors as one doi-self regex term that matches it in any ASCII letter case, bare or behind http(s)://, dx., doi.org/, or doi: in any case, whichever form the record holds; it stays self-only and exact (no part-of links, no version suffixes). Nonblank values must contain a complete DOI (10. followed by digits, /, and a non-whitespace suffix) or numeric PMID; malformed and prefix-only values fail before a request. Omitted or genuinely blank fields remain unset
  • ror_id takes a ROR ID bare (00f54p054) or as a ror.org URL (https://ror.org/…, ror.org/…, a www. host, a trailing slash), in either letter case, and is reduced to the https://ror.org/<lowercase id> form ORCID indexes; a value that is not a ROR ID, or whose check digits do not match, is rejected before any search runs
  • grant_number phrase-matches the grant numbers on researchers' funding items, case-insensitively, over the parts between separators such as hyphens and slashes — 5F31MH010500 also matches 5F31MH010500-03, but a number cut mid-part matches nothing — pair with orcid_get_funding to inspect each match
  • rows: results per page, default 20; a larger value (up to 10,000) is clamped to 1,000, the most ORCID serves per request, and a notice names both sizes on both surfaces. start: 0–10,000 offset pagination (the ORCID Public API's ceiling for unauthenticated requests)
  • A page returns rows results, fewer only at the end of the matches; nextStart is start plus the number returned while matches remain
  • Returns expanded-search results with inline name and institution data — no follow-up profile fetch needed for basic discovery
  • Use for precise field-anchored lookups; use orcid_resolve_researcher for ambiguous names needing ranked disambiguation

orcid_get_profile tool

  • Accepts a bare ORCID iD (0000-0001-2345-6789) or an orcid.org URI (https://orcid.org/…, orcid.org/…, a www. host, a trailing slash); a lowercase x check digit is canonicalized to X. Every tool that takes orcid_id accepts the same forms; the orcid://researcher/{orcid_id}/… resources take the bare iD
  • A deprecated iD — one ORCID merged into another account — resolves to the primary record on every record tool and both resources, and orcidId/orcidUri report the primary iD; on the tools, selfAsserted is judged against it and a notice names both iDs. The three endpoints ORCID does not redirect are resolved through a /person merge check; when that check cannot run, the answer says its result is unconfirmed and to call again
  • Returns name, other names (former names, transliterations, initialed forms), biography, keywords, researcher URLs, external identifiers (Scopus Author ID, ResearcherID, Loop, etc.), emails, and country codes — all in one response
  • Each email carries verified as ORCID publishes it (shown in the text as (verified) / (unverified)); ORCID exposes only verified addresses publicly, so it reads true in practice
  • include_history (default false) reads the full /record in place of /person, still one request, and adds history: createdDate, creationMethod (API, DIRECT, MEMBER_REFERRED, WEBSITE), claimed, verifiedEmail (private addresses included), verifiedPrimaryEmail, and lastModifiedDate, each only when ORCID published it. These are the record's trust signals. The upstream response can exceed 10 MB for a heavy publisher, and the first call for such a record can time out while ORCID builds it (call again); the activities summary is never parsed and the tool output stays small
  • Only publicly visible fields are returned; researchers control per-field visibility. A notice names every section with no public data (e.g. "no public email addresses or countries"), since an empty section can be private rather than empty
  • Entry point for building a researcher dossier before fetching works or affiliations

orcid_get_works tool

  • work_types keeps works of the listed types (ORCID's 58-value vocabulary, e.g. journal-article, preprint, data-set; any listed type matches, an empty list filters nothing); year_from and year_to keep works published in that inclusive range, read from the first four digits of publicationDate. Under a year bound, undated works drop out and a notice counts them. The filters run over the whole record before paging, at no extra upstream cost: matchedCount counts the matches, workCount the whole record, and appliedFilters echoes what was applied
  • Returns 25 matching works by default; limit is clamped to 1,000 (accepted up to 10,000) with a notice naming both sizes. Page with offset and the returned nextOffset; a page holds limit works, fewer only at the end, and truncated says more remain. An offset past the matches returns a notice saying so; no match returns a notice naming the filters and workCount
  • Set include_external_ids to false to drop DOI/PMID/arXiv/ISBN identifier lists for a lighter payload
  • One record per ORCID work group; its identifiers are the group's — the preferred version's own, then any that another source holds, such as a PMID beside a Crossref DOI
  • External identifiers are pre-formatted for chaining to Crossref, PubMed, or arXiv
  • Summaries only — pass a work's putCode to orcid_get_work_detail for abstracts and contributor lists
  • Each work lists its sources — the researcher, or member organizations such as Crossref or a university system — with selfAsserted marking what the researcher asserted; an empty list does not mean no publications

orcid_get_work_detail tool

  • put_codes: 1–1,000 raw codes per call (from orcid_get_works), deduplicated in first-occurrence order before fetching the first 100 distinct codes in one request; every record ORCID returns for them comes back, and a notice names the input cap when applied
  • Returns abstract, contributors with CRediT roles, the record's external IDs, citation metadata (BibTeX or other deposited formats), journal title, and URL
  • A record listing more than 100 contributors keeps the first 100 plus the researcher's own entries, matched by ORCID iD, with contributorCount and contributorsTruncated marking the cut; a citation over 8,192 bytes is left out and flagged citationOmitted, so a large-collaboration paper costs about what its other fields do. Even so, 100 large-collaboration records run past 1 MB: size batches to what the step needs
  • Each put-code is one source's version of the work, so its identifiers can be fewer than orcid_get_works lists for the work group; sources names that source
  • Per-put-code failures (not found or inaccessible) arrive as errors entries — the rest of the batch still resolves
  • deferredPutCodes lists, in request order, the distinct codes beyond the input cap and any ORCID's answer left out; pass it as put_codes in another call. Notices distinguish the two causes
  • An upstream rate limit surfaces as a RateLimited error carrying ORCID's retryAfter when it sent one

orcid_get_affiliations tool

  • types filters which sections to return: employment, education, invited-positions, distinctions, memberships, qualifications, services, or all — default is employment + education; an explicit empty list is rejected
  • One upstream call regardless of how many types are requested
  • Returns organization name, disambiguated ID (ROR/GRID/Ringgold), department, role, and date range per record
  • Each record's sources names who added it — the researcher, or a member organization such as a university research information system; an empty result does not mean no affiliation

orcid_get_funding tool

  • Without put_code, returns the complete grouped funding list in one request with view: summary; each preferred summary exposes its optional putCode
  • Returns funding type (grant, contract, award, salary-award), funder name and disambiguated ID (Crossref Funder ID/ROR), grant numbers, and funding period
  • One record per ORCID funding group, from its preferred version — a grant deposited twice counts once in fundingCount; when the group's versions record distinct award periods, such as renewals under one grant number, periods lists each
  • Supply a summary putCode as put_code for view: detail: fetches only that deposit, with its own source and optional description, URL, amount: { value?, currency? }, organizationDefinedType (the deposit's funding subtype, free text, present only when deposited), and contributors (name?, orcidId?, role?: lead, co-lead, supported-by, or other-contribution). Decimal text is preserved exactly; missing amounts and currencies stay absent
  • contributors is always present in detail ([] when none was deposited, which is not evidence the researcher had no role), in upstream order and whole, and never in summary
  • The deposited description arrives whole (ORCID caps it at 5,000 characters); the text surface represents it as a JSON string so original CRLF line endings survive
  • An unavailable selected deposit returns funding_not_found and denied public access returns funding_inaccessible; each error explains how to recover
  • Funding comes from the researcher or from member organizations (funders, institutions, search-and-link tools), and each record's sources names which; most researchers with real grants have no entries here, and absence does not imply no funding

orcid_get_peer_reviews tool

  • Pages the history in upstream order with offset (default 0) and limit (default 25; a larger value, up to 10,000, is clamped to 1,000 with a notice naming both sizes on both surfaces)
  • reviewCount counts returned reviews, limit of them, fewer only at the end; totalCount reports the full history. Continue with nextOffset when truncated is true. Empty and past-end pages retain the total with no continuation, and an offset past a non-empty history returns a notice saying so
  • Returns reviewer role (reviewer, editor, chair, etc.), review type, completion date, an ISSN-keyed group identifier, and the convening organization ORCID records per record
  • The convening organization is often the service that imported the review (Publons, Clarivate) rather than the journal; ORCID returns no journal name, so the ISSN is the journal key and heads each review that has one
  • Reviews come from the researcher or from member organizations that import them, and each record's sources names which; coverage varies widely by researcher

orcid_get_research_resources tool

  • Covers compute allocations, equipment access, lab facilities, data resources, and clinical study registrations
  • A newer, sparsely populated ORCID section — most researchers have zero entries, and absence does not imply none exist
  • Entries are typically deposited by resource-allocation systems (e.g. ACCESS, XSEDE) rather than added by the researcher
  • Returns resource title, hosting organization (with disambiguated ID), external identifiers (often a portal URI), access period, and the sources that deposited it
  • Default view: summary lists proposals; proposalHosts includes every proposal host, while hostOrganization keeps the first host for compatibility
  • Supply a proposal's putCode as put_code for view: detail: each item carries its name, type, all operators in hosts, external identifiers, and URL; proposal provenance stays on the resource record
  • Detail pages return item_limit items from item_offset: item_offset defaults to 0, item_limit to 25, and a larger item_limit returns at most 100 (accepted maximum 10,000); both require put_code. itemCount, returnedItemCount, itemOffset, itemsTruncated, and nextItemOffset describe the page; top-level truncated mirrors itemsTruncated, and itemLimitNotice discloses a reduced limit on both surfaces
  • Each page repeats the proposal metadata; resume at nextItemOffset with the same put_code. Empty and past-end pages have no continuation

orcid_resolve_researcher tool

  • Returns ranked candidates (rows default 5; a larger value, up to 10,000, returns at most 20 at every search stage) with transparent disambiguation signals: name match type (exact/partial/other-name/none), institution overlap flag, and anchor type (doi/pmid/none). Each candidate carries otherNames, the other names on its ORCID record, verbatim
  • One notice joins, in order: the requested and effective sizes when capped; that the candidates were found by the DOI or PMID alone because no record matched the name with the anchors supplied (it names every anchor you gave); and, when totalFound exceeds the candidates ranked, The ranking covers N of T records matching queryUsed, with the rows value to call again with (up to 20) and, past 20, how to list the rest: orcid_search_researchers with query set to queryUsed and start set to N, which returns them in ORCID's relevance order without match signals. With no candidates it carries the empty-result guidance instead. The notice is plain text in structuredContent and escaped only in content[]
  • Name and institution comparisons are case- and accent-insensitive — José Baselga and Jose Baselga classify the same candidate identically — and compare a dash both ways, dropped and as a space: Min-Jun matches Minjun, Jean-Pierre matches Jean Pierre, and a dashed record word also offers its parts, so Wei matches in Qian-Wei
  • When doi or pmid is provided (bare or as a URL), uses doi-self or pmid-self as an anchor — researchers who have linked that work to their ORCID record are near-deterministic matches
  • Accepts a full name (Jennifer Doudna), a byline with initials (J. Doudna, Jennifer A. Doudna), or Family, Given (Doudna, Jennifer, read as Jennifer Doudna); an initial counts toward a partial match when the candidate's first given name starts with it
  • Searches the exact name phrase first, so a name that matches as written sends one query. Each later stage runs only when every earlier one found nothing: the byline form of any initials with the affiliation, then the phrase and the byline without it, then the other names listed on ORCID records, then each supplied anchor alone
  • No synthetic scores — raw signal fields only, so callers can apply their own ranking logic

orcid://researcher/{orcid_id}/profile resource

  • Returns name, other names, biography, keywords, researcher URLs, and external identifiers as application/json
  • {orcid_id} is the bare iD, with an X or x check digit — a URI segment cannot carry the https://orcid.org/ form
  • Fails with a typed data.reason and a recovery hint, like the tools: invalid_orcid_id for a checksum-invalid iD (rejected locally, before any upstream call), profile_not_found for an iD ORCID does not know or a record with no public name
  • Prefer the orcid_get_profile tool when the response needs to flow into conditional logic

orcid://researcher/{orcid_id}/works resource

  • Returns the first 25 works plus workCount (the total available) as application/json
  • {orcid_id} is the bare iD, with an X or x check digit
  • Fails with invalid_orcid_id (checksum, before any upstream call) or profile_not_found (unknown iD, data.orcidId included), each with a recovery hint
  • No cursor pagination on this resource — use the orcid_get_works tool to page the full list or filter results
  • DOIs and PMIDs in the response are ready for Crossref or PubMed chaining

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.

ORCID-specific:

  • ORCID Public API v3.0 (https://pub.orcid.org/v3.0) — no API key required for public read endpoints
  • expanded-search as the primary search backend — returns ORCID iD, name, and institution data inline, eliminating N+1 profile fetches
  • Single /activities call for affiliation queries, filtered client-side — eliminates up to 7 parallel upstream calls vs. per-section fetching
  • External identifiers (DOIs, PMIDs, arXiv IDs) surfaced in works responses in formats ready for cross-server chaining to Crossref, PubMed, or arXiv
  • Inline markup that depositing systems leave in work titles, abstracts, and funding and research-resource titles (<i>, <sup>, <h4>) is stripped to plain text; the deposited citation is relayed verbatim

Agent-friendly output:

  • Provenance — orcid_resolve_researcher returns raw disambiguation signals (name match type, institution overlap, anchor type) instead of a synthetic confidence score
  • Who asserted each item — every record from the six activity tools carries sources: the person or member organization that added it (a university system, funder, Crossref, Web of Science) and whether the researcher asserted it (selfAsserted); grouped works and funding list every source in the group
  • Truncation awareness — pages are sized by count alone and a request over a tool's cap returns the cap with a notice; orcid_search_researchers reports numFound and a truncated flag against the ORCID Public API's 10,000-offset ceiling, with nextStart to continue; orcid_get_works reports workCount, matchedCount, and truncated against the requested page, and orcid_get_peer_reviews totalCount and truncated, each with nextOffset to continue; orcid_get_research_resources detail reports truncated with nextItemOffset
  • Merged accounts — a deprecated ORCID iD is served from the primary record it was merged into, reported under the primary iD with a notice naming both, including on the three endpoints ORCID does not redirect (bulk work detail, research resources, allocation detail), where a /person merge check finds the primary iD; if that check cannot run, the answer opens with a notice that its empty or not-found result is unconfirmed and to call again
  • Partial failure isolation — orcid_get_work_detail returns per-put-code errors alongside successfully resolved works instead of failing the whole batch, and names any put-codes past the 100-code fetch cap or missing from ORCID's answer
  • Empty-result guidance — orcid_get_works, orcid_get_affiliations, orcid_get_funding, orcid_get_peer_reviews, and orcid_get_research_resources return a notice when a result is empty, explaining that this may mean neither the researcher nor a member organization added entries, or that visibility settings hide them, rather than confirmed absence; orcid_get_profile names each section with no public data
  • Record text marked as data — in the text output, biographies and abstracts render as blockquotes, names, titles, and organization names are kept to one line, and a deposited citation sits in a code fence it cannot close, so text a researcher or depositing system wrote never reads as the server's own headings or labels; structuredContent carries every value verbatim

Getting started

Connect to the hosted instance, no install:

sh
claude mcp add --transport http orcid-mcp-server https://orcid.caseyjhand.com/mcp

Or run it locally:

sh
claude mcp add orcid-mcp-server -- npx -y @cyanheads/orcid-mcp-server

For other clients, add this to the MCP config file:

json
{  "mcpServers": {    "orcid-mcp-server": {      "command": "npx",      "args": ["-y", "@cyanheads/orcid-mcp-server"]    }  }}

No API key is required: the ORCID Public API is open for public read access, for non-commercial use under ORCID Public API ToS §2. For Docker or a source build, see Running the server.

Configuration

All configuration is validated at startup via Zod schemas in src/config/server-config.ts. Key environment variables:

VariableDescriptionDefault
ORCID_API_BASE_URLOverride the ORCID API base URL. Useful for pointing at the sandbox (https://pub.sandbox.orcid.org/v3.0/).https://pub.orcid.org/v3.0
MCP_TRANSPORT_TYPETransport: stdio or httpstdio
MCP_HTTP_PORTHTTP server port3010
MCP_HTTP_ENDPOINT_PATHHTTP endpoint path/mcp
MCP_SESSION_MODEHTTP session mode: auto, stateful, or stateless. This server declares stateless in createApp() — no tool asks the caller for input mid-handler — and a set value overrides it.stateless
MCP_PUBLIC_URLPublic origin for TLS-terminating reverse-proxy deploymentsnone
MCP_AUTH_MODEAuthentication: none, jwt, or oauthnone
MCP_LOG_LEVELLog level (debug, info, warning, error, etc.)info
MCP_GC_PRESSURE_INTERVAL_MSOpt-in Bun-only forced-GC pressure loop (ms). Try 60000 if heap growth is observed under sustained HTTP load.0 (disabled)
LOGS_DIRDirectory for log files (Node.js only)<project-root>/logs
STORAGE_PROVIDER_TYPEStorage backend: in-memory, filesystem, supabase, cloudflare-kv/r2/d1in-memory
OTEL_ENABLEDEnable OpenTelemetryfalse

See .env.example for the full list of optional overrides.

Running the server

Local development

Requires Bun v1.4.4 or higher (or Node.js v24+).

  • Clone and install:

    sh
    git clone https://github.com/cyanheads/orcid-mcp-server.gitcd orcid-mcp-server && bun installcp .env.example .env   # no required variables
  • Build and run:

    sh
    # One-time buildbun run rebuild
    # Run the built serverbun run start:stdio# orbun run start:http
  • Run checks and tests:

    sh
    bun run devcheck   # Lint, format, typecheck, securitybun run test       # Vitest test suitebun run lint:mcp   # Validate MCP definitions against spec

Docker

sh
docker run --rm -p 3010:3010 ghcr.io/cyanheads/orcid-mcp-server:latest

The image defaults to HTTP transport, stateless session mode, and logs to /var/log/orcid-mcp-server. To run it over stdio from an MCP client, use "command": "docker" with "args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "ghcr.io/cyanheads/orcid-mcp-server:latest"]. To build locally, docker build -t orcid-mcp-server .; OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

DirectoryPurpose
src/index.tscreateApp() entry point — registers tools and resources, inits services.
src/configServer-specific environment variable parsing and validation with Zod.
src/mcp-server/toolsTool definitions (*.tool.ts). Nine tools across search, disambiguation, profile, works, work detail, affiliations, funding, peer reviews, and research resources.
src/mcp-server/resourcesResource definitions (*.resource.ts). Profile and works resources.
src/services/orcidORCID Public API v3.0 service layer — search, record section fetchers, retry/backoff.
skills/Agent skill published over MCP and in the npm package, Docker image, and .mcpb bundle (orcid-guide).
tests/Unit and integration tests mirroring src/.

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

  • Handlers throw, framework catches — no try/catch in tool logic
  • Use ctx.log for request-scoped logging, ctx.state for tenant-scoped storage
  • Register new tools and resources in the createApp() arrays
  • Wrap ORCID API calls: validate raw response → normalize to domain type → return output schema; never fabricate missing fields

Contributing

Issues are welcome. Run checks and tests before submitting:

sh
bun run devcheckbun run test

License

Apache-2.0 — see LICENSE for details.

來源:README.md,提交 16c6ab1

工具

9

orcid_get_profile

Get ORCID Researcher Profile

Fetch a researcher's public profile from ORCID: name, other names, biography, keywords, researcher URLs, external identifiers such as Scopus Author ID, ResearcherID, and Loop profile, public email addresses with their verified flags, and countries. This is the entry point for building a researcher dossier. Pass a bare ORCID iD (0000-0001-2345-6789) or a full URI (https://orcid.org/0000-0001-2345-6789). Set include_history for the record's trust signals: when and how it was created, whether the researcher claimed it, and whether it has a verified email, private addresses included. The profile contains only publicly visible data — researchers control visibility per field.

輸入參數orcid_id必填include_history

orcid_search_researchers

Search ORCID Researchers

Search the ORCID registry using structured field parameters or raw Solr syntax. Provide at least one non-blank search field; all provided structured params are ANDed together. The `query` field adds raw Solr syntax, ANDed with the structured params as one group. Returns ORCID iDs with inline name and institution data — no follow-up profile fetches needed for basic disambiguation. For ranked disambiguation of an ambiguous author name, use orcid_resolve_researcher instead. Continue a page from nextStart; the ORCID Public API pages only the first 10,000 matches, so narrow the query to reach the rest.

輸入參數doipmidrowsquerystartror_idkeywordgiven_nameaffiliationfamily_namegrant_number

orcid_get_works

Get ORCID Researcher Works

Retrieve works associated with an ORCID iD — publications, datasets, software, preprints, and more. Returns work summaries with put-codes, titles, types, publication dates, journal names, and all external identifiers (DOIs, PMIDs, arXiv IDs, ISBNs). Narrow the list with work_types and year_from/year_to; the filters run over the whole record before paging, so matchedCount counts every match and workCount the whole record. The first 25 matching works are returned by default; page with offset and the returned nextOffset, or raise limit. Set include_external_ids to false to omit identifier lists for a lighter payload. Pass the putCode from each work to orcid_get_work_detail to retrieve the full record including abstract and contributors. External IDs are ready for chaining to Crossref, PubMed, or arXiv servers. Works come from the researcher or from member organizations such as Crossref or a university system; each work lists its sources and whether the researcher asserted it (selfAsserted). A researcher may not have linked all their publications.

輸入參數limitoffsetyear_toorcid_id必填year_fromwork_typesinclude_external_ids

orcid_get_work_detail

Get ORCID Work Details (Bulk)

Fetch full work details by put-code from orcid_get_works. Accepts 1–1,000 raw codes, deduplicates in first-occurrence order, and fetches the first 100 distinct codes in one request, returning every record ORCID sends. Returns abstracts, contributors with CRediT roles, the record's external IDs (DOI, PMID, arXiv, ISBN, etc.), citation metadata, journal title, URL, and source provenance. A record listing more than 100 contributors keeps the first 100 plus the requested researcher's own entries, with contributorCount and contributorsTruncated; a citation over 8,192 bytes is left out and flagged by citationOmitted. Per-record errors are returned alongside successful works. deferredPutCodes lists, in request order, the codes past the 100-code fetch cap and any ORCID returned no result for; pass them as put_codes in another call.

輸入參數orcid_id必填put_codes必填

orcid_get_affiliations

Get ORCID Researcher Affiliations

Fetch affiliation records for an ORCID researcher. The `types` parameter controls which affiliation sections to return: employment, education, invited-positions, distinctions, memberships, qualifications, services, or all. Default is employment and education. Returns organization names, disambiguated organization identifiers (ROR/GRID/Ringgold), departments, roles, date ranges, and sources. Affiliations come from the researcher or from member organizations such as a university research information system; sources names who added each, and selfAsserted tells the two apart. Absence does not mean no affiliation.

輸入參數typesorcid_id必填

orcid_get_funding

Get ORCID Researcher Funding

List funding for an ORCID researcher, or supply a summary putCode as put_code to fetch one deposited award. Summary returns one preferred record per grant group with all sources and distinct periods. Detail returns that deposit alone with its own source, optional exact decimal amount and currency, URL, funding subtype, contributors with their roles (lead, co-lead, supported-by), and its whole deposited description (ORCID caps it at 5,000 characters). Funding records are sparse; absence does not imply no funding.

輸入參數orcid_id必填put_code

orcid_get_peer_reviews

Get ORCID Researcher Peer Reviews

Fetch peer review activity for an ORCID researcher: reviewer role (reviewer, editor, chair, etc.), review type, completion dates, ISSN-keyed group identifiers, and the convening organization as ORCID records it — often the service that imported the review (e.g. Publons, Clarivate). ORCID returns no journal name; groupIssn is the key to the journal, and a review that has one is headed by it. Use to assess editorial activity, journal affiliations, and the scope of a researcher's peer review contributions. Reviews come from the researcher or from member organizations that import them; sources names who added each, and coverage varies by researcher.

輸入參數limitoffsetorcid_id必填

orcid_get_research_resources

Get ORCID Research Resources

List allocation proposals for an ORCID researcher, or supply put_code from a summary record to retrieve its actual resource items. Summary is the default view and includes every proposal host, identifiers, access period, and source provenance; hostOrganization remains the first proposal host. Detail adds item names, types, all operators, identifiers, and URLs, paged by item_offset and item_limit (both require put_code); continue at nextItemOffset with the same put_code. Most researchers have no entries; allocation systems such as ACCESS deposit these records.

輸入參數orcid_id必填put_codeitem_limititem_offset

orcid_resolve_researcher

Resolve ORCID Researcher

Disambiguate an author name to a verified ORCID iD. Returns ranked candidates (5 by default, at most 20 per search stage) with transparent disambiguation signals — name match type (exact/partial/other-name/none), institution overlap flag, and whether a DOI or PMID anchor was used in the query — plus the other names listed on each record. The name is searched as an exact phrase first; when that finds nothing, byline initials (J. Doudna, Jennifer A. Doudna) and then the other names listed on ORCID records are tried. A DOI or PMID anchor is near-deterministic — it filters to researchers who have linked that specific work to their ORCID record; when no name query finds a record with it, each anchor is tried alone and the notice says the candidates were found by the anchor alone. The ranking covers only the candidates returned: when totalFound is larger, the notice gives the rows value that ranks more and the orcid_search_researchers call that lists the rest, without match signals. Use this tool (not orcid_search_researchers) when the input is an ambiguous name that needs ranked disambiguation. No synthetic scores are used — raw signals only.

輸入參數doiname必填pmidrowsaffiliation

版本歷史

8
  1. v0.4.1最新Nov 16, 2026
  2. v0.4.0Oct 29, 2026
  3. v0.3.4Oct 25, 2026
  4. v0.3.3Oct 18, 2026
  5. v0.3.2Oct 3, 2026
  6. v0.3.1Sep 24, 2026
  7. v0.2.17Sep 22, 2026
  8. v0.2.16Sep 16, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分