Nine tools organized around three workflows — author disambiguation, researcher profiling, and cross-server identifier chaining:

Search the ORCID registry with structured field parameters mapped to Solr field queries.

• Structured params — given_name, family_name, affiliation, keyword, ror_id, doi, pmid — are ANDed into a Solr query automatically
• doi and pmid translate to doi-self and pmid-self field queries: "who has linked this work to their ORCID record?"
• query appends raw Solr to the generated clause for advanced use
• ror_id values (full URLs like https://ror.org/00f54p054) are quoted internally to handle Solr's colon parsing
• Returns expanded-search results with inline name and institution data — no follow-up profile fetch needed for basic discovery
• Use this for precise field-anchored lookups; use orcid_resolve_researcher for ambiguous names needing ranked disambiguation

Fetch a researcher's public person section by ORCID iD.

• Accepts bare ORCID iD (0000-0001-2345-6789) or full URI form
• Returns name, biography, keywords, researcher URLs, addresses, and external identifiers (Scopus Author ID, ResearcherID, Loop, etc.)
• External identifiers are embedded in the person response — no separate round-trip
• Entry point for building a researcher dossier before fetching works or affiliations

Retrieve the works list for a researcher.

• Returns work summaries: title, type, publication date, journal name, and all external identifiers (DOI, PMID, arXiv ID, ISBN, etc.)
• External IDs are returned in formats consumable by downstream servers (Crossref, PubMed, arXiv)
• Works list is summaries only — chain to the relevant server for full metadata or abstracts

Fetch full detail records for 1–100 works in a single bulk request using the ORCID bulk works endpoint.

• put_codes is an array of 1–100 put-codes from orcid_get_works
• Single round-trip regardless of how many put-codes are requested
• Returns abstracts, all contributors with CRediT roles, the complete external ID list, citation metadata (BibTeX or other formats when deposited), journal title, and URL for each work
• Per-record errors (not-found or inaccessible put-codes) arrive as errors entries — the remaining works still resolve

Fetch affiliation records by type, using a single /activities call filtered client-side.

• types controls which sections to include: employment, education, invited-positions, distinctions, memberships, qualifications, services, or all
• Default is ['employment', 'education'] (the 90% case)
• Returns organization names, disambiguated org IDs (ROR/GRID/Ringgold), departments, roles, and date ranges
• One upstream call regardless of how many types are requested — the /activities endpoint returns all sections at once

Fetch funding records for a researcher.

• Returns grants, contracts, awards, and salary awards with funder names, grant numbers, and funding periods
• Funding data is self-reported and often sparse — absence does not mean no funding
• Useful when it exists; high-value (grant numbers, funder IDs) but a thin single-endpoint wrapper

Fetch peer review activity for a researcher.

• Returns convening organizations (journals/publishers), reviewer role (reviewer, editor, chair, etc.), review type, completion dates, and ISSN-keyed group identifiers
• Useful for assessing editorial activity and journal affiliations

List research resources associated with a researcher.

• Covers compute allocations, equipment access, lab facilities, data resources, and clinical study registrations
• A newer ORCID section that is sparsely populated — most researchers have no 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 org ID), external identifiers (often a portal URI), and access period

Disambiguate an author name to a verified ORCID iD.

• Returns up to 5 ranked candidates with transparent disambiguation signals: name match type (exact/partial/other-name), institution overlap flag, and anchor type (doi/pmid/none)
• When doi or pmid is provided, 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
• No synthetic scores — raw signal fields only, so callers can apply their own ranking logic

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.

Built on @cyanheads/mcp-ts-core:

• Declarative tool and resource definitions — single file per primitive, framework handles registration and validation
• Unified error handling — handlers throw, framework catches, classifies, and formats
• Pluggable auth: none, jwt, oauth
• Swappable storage backends: in-memory, filesystem, Supabase, Cloudflare KV/R2/D1
• Structured logging with optional OpenTelemetry tracing
• STDIO and Streamable HTTP transports

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

Agent-friendly output:

• Transparent disambiguation signals in orcid_resolve_researcher — name match type, institution overlap, and anchor type are returned as raw fields, not a synthetic score, so agents can reason about match confidence
• Known-limitation annotations — works list surfaces num_found so agents know when the 10,000-result public API cap was hit; funding and profile tools note when sections are empty due to researcher-controlled visibility
• External identifier pass-through — DOIs, PMIDs, arXiv IDs, Scopus Author IDs are normalized to formats consumable by downstream servers without parsing

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"
    }
  }
}

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

• Bun v1.3.2 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.

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

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.

• Build and run:

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

• Run checks and tests:

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

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.

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

Issues and pull requests are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

Apache-2.0 — see LICENSE for details.