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 from any MCP client. Runs as a stdio process, a local Streamable HTTP server, or the public hosted endpoint above.

Tools

Resources

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.

Capability reference

orcid_search_researchers _tool

• Structured params — given_name, family_name, affiliation, keyword, ror_id, doi, pmid, grant_number — AND together automatically; query appends raw Solr syntax to the generated clause
• At least one param must be non-blank — an empty or whitespace-only search is rejected rather than run against the whole registry
• 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
• 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: 1–1000 (default 20); start: 0–10,000 offset pagination (the ORCID Public API's ceiling for unauthenticated requests)
• 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 a full URI
• Returns name, biography, keywords, researcher URLs, external identifiers (Scopus Author ID, ResearcherID, Loop, etc.), emails, and country codes — all in one response
• Only publicly visible fields are returned; researchers control per-field visibility
• Entry point for building a researcher dossier before fetching works or affiliations

orcid_get_works _tool

• Returns the first 50 works by default (limit max 1000); page with offset and the returned nextOffset — workCount reports the total available
• A page also stops before its structured output or its text would pass 64,000 bytes, so returnedCount can come in below limit; truncated and nextOffset carry the continuation either way
• Set include_external_ids to false to drop DOI/PMID/arXiv/ISBN identifier lists for a lighter payload
• 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 full contributor lists
• Works are self-reported; an empty list does not mean no publications

orcid_get_work_detail _tool

• put_codes: 1–100 per call (from orcid_get_works), resolved in a single round-trip; a repeated put-code is fetched once
• Returns abstract, full contributor list with CRediT roles, complete external ID list, citation metadata (BibTeX or other deposited formats), journal title, and URL
• Per-put-code failures (not found or inaccessible) arrive as errors entries — the rest of the batch still resolves
• Records are added until the structured output or the text would pass 64,000 bytes; put-codes left out come back in deferredPutCodes with a notice, ready to pass as put_codes in the next call
• 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
• Self-reported; an empty result does not mean no affiliation

orcid_get_funding _tool

• No filtering params — returns the complete funding list for the ORCID iD in one call
• Returns funding type (grant, contract, award, salary-award), funder name and disambiguated ID (Crossref Funder ID/ROR), grant numbers, and funding period
• Entirely self-reported — most researchers with real grants have no entries here; absence does not imply no funding

orcid_get_peer_reviews _tool

• No filtering params — returns the complete peer review history for the ORCID iD in one call
• Returns convening organization (journal/publisher), reviewer role (reviewer, editor, chair, etc.), review type, completion date, and an ISSN-keyed group identifier per record
• Self-reported or imported by participating publishers — 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 self-reported
• Returns resource title, hosting organization (with disambiguated ID), external identifiers (often a portal URI), and access period

orcid_resolve_researcher _tool

• Returns ranked candidates (5 default, up to 20 via rows) with transparent disambiguation signals: name match type (exact/partial/other-name/none), institution overlap flag, and anchor type (doi/pmid/none)
• Name and institution comparisons are case- and accent-insensitive — José Baselga and Jose Baselga classify the same candidate identically
• 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
• Falls back to a relaxed query (dropping affiliation) if the initial candidate set is empty, then to anchor-only retries when a supplied anchor is present
• No synthetic scores — raw signal fields only, so callers can apply their own ranking logic

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

• Returns name, biography, keywords, researcher URLs, and external identifiers as application/json
• Rejects a checksum-invalid ORCID iD locally before any upstream call
• 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
• 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
• Truncation awareness — orcid_search_researchers reports numFound and a truncated flag against the ORCID Public API's 10,000-offset ceiling; orcid_get_works reports workCount and truncated against its own page size and a 64,000-byte response budget
• 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 the response budget deferred
• 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 reflect self-reporting gaps or visibility settings rather than confirmed absence

Getting started

Public Hosted Instance

A public instance is available at https://orcid.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:

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

Self-Hosted / Local

Add the following to your MCP client configuration file. No API key is required — the ORCID Public API is open for public read access.

{
  "mcpServers": {
    "orcid-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/orcid-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "orcid-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/orcid-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "orcid-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "MCP_TRANSPORT_TYPE=stdio",
        "ghcr.io/cyanheads/orcid-mcp-server:latest"
      ]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

• Bun v1.4.0 or higher (or Node.js v24+).
• No API key required. The ORCID Public API is open for public read access. Non-commercial use only under ORCID Public API ToS §2.

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/orcid-mcp-server.git

2. Navigate into the directory:

cd orcid-mcp-server

3. Install dependencies:

bun install

4. Configure environment:

cp .env.example .env
# edit .env if needed — no required vars

Configuration

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

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

Running the server

Local development

• Build and run:

  sh

  # One-time build
  bun run rebuild
  
  # Run the built server
  bun run start:stdio
  # or
  bun run start:http
  

• Run checks and tests:

  sh

  bun run devcheck   # Lint, format, typecheck, security
  bun run test       # Vitest test suite
  bun run lint:mcp   # Validate MCP definitions against spec
  

Docker

docker build -t orcid-mcp-server .
docker run --rm -p 3010:3010 orcid-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/orcid-mcp-server. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

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:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.